Methods, systems and devices for detecting threatening objects and for classifying magnetic data

DOEpatents

Kotter, Dale K [Shelley, ID; Roybal, Lyle G [Idaho Falls, ID; Rohrbaugh, David T [Idaho Falls, ID; Spencer, David F [Idaho Falls, ID

2012-01-24

A method for detecting threatening objects in a security screening system. The method includes a step of classifying unique features of magnetic data as representing a threatening object. Another step includes acquiring magnetic data. Another step includes determining if the acquired magnetic data comprises a unique feature.

Automatic identification of fault surfaces through Object Based Image Analysis of a Digital Elevation Model in the submarine area of the North Aegean Basin

NASA Astrophysics Data System (ADS)

Argyropoulou, Evangelia

2015-04-01

The current study was focused on the seafloor morphology of the North Aegean Basin in Greece, through Object Based Image Analysis (OBIA) using a Digital Elevation Model. The goal was the automatic extraction of morphologic and morphotectonic features, resulting into fault surface extraction. An Object Based Image Analysis approach was developed based on the bathymetric data and the extracted features, based on morphological criteria, were compared with the corresponding landforms derived through tectonic analysis. A digital elevation model of 150 meters spatial resolution was used. At first, slope, profile curvature, and percentile were extracted from this bathymetry grid. The OBIA approach was developed within the eCognition environment. Four segmentation levels were created having as a target "level 4". At level 4, the final classes of geomorphological features were classified: discontinuities, fault-like features and fault surfaces. On previous levels, additional landforms were also classified, such as continental platform and continental slope. The results of the developed approach were evaluated by two methods. At first, classification stability measures were computed within eCognition. Then, qualitative and quantitative comparison of the results took place with a reference tectonic map which has been created manually based on the analysis of seismic profiles. The results of this comparison were satisfactory, a fact which determines the correctness of the developed OBIA approach.

Color distributions in E-S0 galaxies. I. Frequency and importance of dust patterns for various brands of E classified galaxies

NASA Astrophysics Data System (ADS)

Michard, R.

1998-06-01

From the consideration of a sample of color distributions in 67 E classified objects of the Local Supercluster, it is found that local dust features are much more frequent and important in disky E's than boxy E's. The subclass of undeterminate objects, those which cannot be assigned to the diE or boE groups, is intermediate. Subsets of objects of common properties are considered from the point of view of local dust features occurrence: giant boxy E's; minor boxy E's with rotational support; compact dwarfs; SB0-like E's. It is noted that the detection of dust features is more than twice less frequent in Virgo cluster ellipticals than in the full sample, but the significance of this result is not clear. Based on observations collected at the Canada-France-Hawaii Telescope and at the Observatoire du Pic du Midi

Intelligent classifier for dynamic fault patterns based on hidden Markov model

NASA Astrophysics Data System (ADS)

Xu, Bo; Feng, Yuguang; Yu, Jinsong

2006-11-01

It's difficult to build precise mathematical models for complex engineering systems because of the complexity of the structure and dynamics characteristics. Intelligent fault diagnosis introduces artificial intelligence and works in a different way without building the analytical mathematical model of a diagnostic object, so it's a practical approach to solve diagnostic problems of complex systems. This paper presents an intelligent fault diagnosis method, an integrated fault-pattern classifier based on Hidden Markov Model (HMM). This classifier consists of dynamic time warping (DTW) algorithm, self-organizing feature mapping (SOFM) network and Hidden Markov Model. First, after dynamic observation vector in measuring space is processed by DTW, the error vector including the fault feature of being tested system is obtained. Then a SOFM network is used as a feature extractor and vector quantization processor. Finally, fault diagnosis is realized by fault patterns classifying with the Hidden Markov Model classifier. The importing of dynamic time warping solves the problem of feature extracting from dynamic process vectors of complex system such as aeroengine, and makes it come true to diagnose complex system by utilizing dynamic process information. Simulating experiments show that the diagnosis model is easy to extend, and the fault pattern classifier is efficient and is convenient to the detecting and diagnosing of new faults.

Using an Improved SIFT Algorithm and Fuzzy Closed-Loop Control Strategy for Object Recognition in Cluttered Scenes

PubMed Central

Nie, Haitao; Long, Kehui; Ma, Jun; Yue, Dan; Liu, Jinguo

2015-01-01

Partial occlusions, large pose variations, and extreme ambient illumination conditions generally cause the performance degradation of object recognition systems. Therefore, this paper presents a novel approach for fast and robust object recognition in cluttered scenes based on an improved scale invariant feature transform (SIFT) algorithm and a fuzzy closed-loop control method. First, a fast SIFT algorithm is proposed by classifying SIFT features into several clusters based on several attributes computed from the sub-orientation histogram (SOH), in the feature matching phase only features that share nearly the same corresponding attributes are compared. Second, a feature matching step is performed following a prioritized order based on the scale factor, which is calculated between the object image and the target object image, guaranteeing robust feature matching. Finally, a fuzzy closed-loop control strategy is applied to increase the accuracy of the object recognition and is essential for autonomous object manipulation process. Compared to the original SIFT algorithm for object recognition, the result of the proposed method shows that the number of SIFT features extracted from an object has a significant increase, and the computing speed of the object recognition processes increases by more than 40%. The experimental results confirmed that the proposed method performs effectively and accurately in cluttered scenes. PMID:25714094

Applying a new unequally weighted feature fusion method to improve CAD performance of classifying breast lesions

NASA Astrophysics Data System (ADS)

Zargari Khuzani, Abolfazl; Danala, Gopichandh; Heidari, Morteza; Du, Yue; Mashhadi, Najmeh; Qiu, Yuchen; Zheng, Bin

2018-02-01

Higher recall rates are a major challenge in mammography screening. Thus, developing computer-aided diagnosis (CAD) scheme to classify between malignant and benign breast lesions can play an important role to improve efficacy of mammography screening. Objective of this study is to develop and test a unique image feature fusion framework to improve performance in classifying suspicious mass-like breast lesions depicting on mammograms. The image dataset consists of 302 suspicious masses detected on both craniocaudal and mediolateral-oblique view images. Amongst them, 151 were malignant and 151 were benign. The study consists of following 3 image processing and feature analysis steps. First, an adaptive region growing segmentation algorithm was used to automatically segment mass regions. Second, a set of 70 image features related to spatial and frequency characteristics of mass regions were initially computed. Third, a generalized linear regression model (GLM) based machine learning classifier combined with a bat optimization algorithm was used to optimally fuse the selected image features based on predefined assessment performance index. An area under ROC curve (AUC) with was used as a performance assessment index. Applying CAD scheme to the testing dataset, AUC was 0.75+/-0.04, which was significantly higher than using a single best feature (AUC=0.69+/-0.05) or the classifier with equally weighted features (AUC=0.73+/-0.05). This study demonstrated that comparing to the conventional equal-weighted approach, using an unequal-weighted feature fusion approach had potential to significantly improve accuracy in classifying between malignant and benign breast masses.

Automated detection of tuberculosis on sputum smeared slides using stepwise classification

NASA Astrophysics Data System (ADS)

Divekar, Ajay; Pangilinan, Corina; Coetzee, Gerrit; Sondh, Tarlochan; Lure, Fleming Y. M.; Kennedy, Sean

2012-03-01

Routine visual slide screening for identification of tuberculosis (TB) bacilli in stained sputum slides under microscope system is a tedious labor-intensive task and can miss up to 50% of TB. Based on the Shannon cofactor expansion on Boolean function for classification, a stepwise classification (SWC) algorithm is developed to remove different types of false positives, one type at a time, and to increase the detection of TB bacilli at different concentrations. Both bacilli and non-bacilli objects are first analyzed and classified into several different categories including scanty positive, high concentration positive, and several non-bacilli categories: small bright objects, beaded, dim elongated objects, etc. The morphological and contrast features are extracted based on aprior clinical knowledge. The SWC is composed of several individual classifiers. Individual classifier to increase the bacilli counts utilizes an adaptive algorithm based on a microbiologist's statistical heuristic decision process. Individual classifier to reduce false positive is developed through minimization from a binary decision tree to classify different types of true and false positive based on feature vectors. Finally, the detection algorithm is was tested on 102 independent confirmed negative and 74 positive cases. A multi-class task analysis shows high accordance rate for negative, scanty, and high-concentration as 88.24%, 56.00%, and 97.96%, respectively. A binary-class task analysis using a receiver operating characteristics method with the area under the curve (Az) is also utilized to analyze the performance of this detection algorithm, showing the superior detection performance on the high-concentration cases (Az=0.913) and cases mixed with high-concentration and scanty cases (Az=0.878).

Gas chimney detection based on improving the performance of combined multilayer perceptron and support vector classifier

NASA Astrophysics Data System (ADS)

Hashemi, H.; Tax, D. M. J.; Duin, R. P. W.; Javaherian, A.; de Groot, P.

2008-11-01

Seismic object detection is a relatively new field in which 3-D bodies are visualized and spatial relationships between objects of different origins are studied in order to extract geologic information. In this paper, we propose a method for finding an optimal classifier with the help of a statistical feature ranking technique and combining different classifiers. The method, which has general applicability, is demonstrated here on a gas chimney detection problem. First, we evaluate a set of input seismic attributes extracted at locations labeled by a human expert using regularized discriminant analysis (RDA). In order to find the RDA score for each seismic attribute, forward and backward search strategies are used. Subsequently, two non-linear classifiers: multilayer perceptron (MLP) and support vector classifier (SVC) are run on the ranked seismic attributes. Finally, to capitalize on the intrinsic differences between both classifiers, the MLP and SVC results are combined using logical rules of maximum, minimum and mean. The proposed method optimizes the ranked feature space size and yields the lowest classification error in the final combined result. We will show that the logical minimum reveals gas chimneys that exhibit both the softness of MLP and the resolution of SVC classifiers.

A New 3D Object Pose Detection Method Using LIDAR Shape Set

PubMed Central

Kim, Jung-Un

2018-01-01

In object detection systems for autonomous driving, LIDAR sensors provide very useful information. However, problems occur because the object representation is greatly distorted by changes in distance. To solve this problem, we propose a LIDAR shape set that reconstructs the shape surrounding the object more clearly by using the LIDAR point information projected on the object. The LIDAR shape set restores object shape edges from a bird’s eye view by filtering LIDAR points projected on a 2D pixel-based front view. In this study, we use this shape set for two purposes. The first is to supplement the shape set with a LIDAR Feature map, and the second is to divide the entire shape set according to the gradient of the depth and density to create a 2D and 3D bounding box proposal for each object. We present a multimodal fusion framework that classifies objects and restores the 3D pose of each object using enhanced feature maps and shape-based proposals. The network structure consists of a VGG -based object classifier that receives multiple inputs and a LIDAR-based Region Proposal Networks (RPN) that identifies object poses. It works in a very intuitive and efficient manner and can be extended to other classes other than vehicles. Our research has outperformed object classification accuracy (Average Precision, AP) and 3D pose restoration accuracy (3D bounding box recall rate) based on the latest studies conducted with KITTI data sets. PMID:29547551

A New 3D Object Pose Detection Method Using LIDAR Shape Set.

PubMed

Kim, Jung-Un; Kang, Hang-Bong

2018-03-16

In object detection systems for autonomous driving, LIDAR sensors provide very useful information. However, problems occur because the object representation is greatly distorted by changes in distance. To solve this problem, we propose a LIDAR shape set that reconstructs the shape surrounding the object more clearly by using the LIDAR point information projected on the object. The LIDAR shape set restores object shape edges from a bird's eye view by filtering LIDAR points projected on a 2D pixel-based front view. In this study, we use this shape set for two purposes. The first is to supplement the shape set with a LIDAR Feature map, and the second is to divide the entire shape set according to the gradient of the depth and density to create a 2D and 3D bounding box proposal for each object. We present a multimodal fusion framework that classifies objects and restores the 3D pose of each object using enhanced feature maps and shape-based proposals. The network structure consists of a VGG -based object classifier that receives multiple inputs and a LIDAR-based Region Proposal Networks (RPN) that identifies object poses. It works in a very intuitive and efficient manner and can be extended to other classes other than vehicles. Our research has outperformed object classification accuracy (Average Precision, AP) and 3D pose restoration accuracy (3D bounding box recall rate) based on the latest studies conducted with KITTI data sets.

A systematic comparison of different object-based classification techniques using high spatial resolution imagery in agricultural environments

NASA Astrophysics Data System (ADS)

Li, Manchun; Ma, Lei; Blaschke, Thomas; Cheng, Liang; Tiede, Dirk

2016-07-01

Geographic Object-Based Image Analysis (GEOBIA) is becoming more prevalent in remote sensing classification, especially for high-resolution imagery. Many supervised classification approaches are applied to objects rather than pixels, and several studies have been conducted to evaluate the performance of such supervised classification techniques in GEOBIA. However, these studies did not systematically investigate all relevant factors affecting the classification (segmentation scale, training set size, feature selection and mixed objects). In this study, statistical methods and visual inspection were used to compare these factors systematically in two agricultural case studies in China. The results indicate that Random Forest (RF) and Support Vector Machines (SVM) are highly suitable for GEOBIA classifications in agricultural areas and confirm the expected general tendency, namely that the overall accuracies decline with increasing segmentation scale. All other investigated methods except for RF and SVM are more prone to obtain a lower accuracy due to the broken objects at fine scales. In contrast to some previous studies, the RF classifiers yielded the best results and the k-nearest neighbor classifier were the worst results, in most cases. Likewise, the RF and Decision Tree classifiers are the most robust with or without feature selection. The results of training sample analyses indicated that the RF and adaboost. M1 possess a superior generalization capability, except when dealing with small training sample sizes. Furthermore, the classification accuracies were directly related to the homogeneity/heterogeneity of the segmented objects for all classifiers. Finally, it was suggested that RF should be considered in most cases for agricultural mapping.

Recognition of pornographic web pages by classifying texts and images.

PubMed

Hu, Weiming; Wu, Ou; Chen, Zhouyao; Fu, Zhouyu; Maybank, Steve

2007-06-01

With the rapid development of the World Wide Web, people benefit more and more from the sharing of information. However, Web pages with obscene, harmful, or illegal content can be easily accessed. It is important to recognize such unsuitable, offensive, or pornographic Web pages. In this paper, a novel framework for recognizing pornographic Web pages is described. A C4.5 decision tree is used to divide Web pages, according to content representations, into continuous text pages, discrete text pages, and image pages. These three categories of Web pages are handled, respectively, by a continuous text classifier, a discrete text classifier, and an algorithm that fuses the results from the image classifier and the discrete text classifier. In the continuous text classifier, statistical and semantic features are used to recognize pornographic texts. In the discrete text classifier, the naive Bayes rule is used to calculate the probability that a discrete text is pornographic. In the image classifier, the object's contour-based features are extracted to recognize pornographic images. In the text and image fusion algorithm, the Bayes theory is used to combine the recognition results from images and texts. Experimental results demonstrate that the continuous text classifier outperforms the traditional keyword-statistics-based classifier, the contour-based image classifier outperforms the traditional skin-region-based image classifier, the results obtained by our fusion algorithm outperform those by either of the individual classifiers, and our framework can be adapted to different categories of Web pages.

A Hybrid Classification System for Heart Disease Diagnosis Based on the RFRS Method.

PubMed

Liu, Xiao; Wang, Xiaoli; Su, Qiang; Zhang, Mo; Zhu, Yanhong; Wang, Qiugen; Wang, Qian

2017-01-01

Heart disease is one of the most common diseases in the world. The objective of this study is to aid the diagnosis of heart disease using a hybrid classification system based on the ReliefF and Rough Set (RFRS) method. The proposed system contains two subsystems: the RFRS feature selection system and a classification system with an ensemble classifier. The first system includes three stages: (i) data discretization, (ii) feature extraction using the ReliefF algorithm, and (iii) feature reduction using the heuristic Rough Set reduction algorithm that we developed. In the second system, an ensemble classifier is proposed based on the C4.5 classifier. The Statlog (Heart) dataset, obtained from the UCI database, was used for experiments. A maximum classification accuracy of 92.59% was achieved according to a jackknife cross-validation scheme. The results demonstrate that the performance of the proposed system is superior to the performances of previously reported classification techniques.

Modeling guidance and recognition in categorical search: bridging human and computer object detection.

PubMed

Zelinsky, Gregory J; Peng, Yifan; Berg, Alexander C; Samaras, Dimitris

2013-10-08

Search is commonly described as a repeating cycle of guidance to target-like objects, followed by the recognition of these objects as targets or distractors. Are these indeed separate processes using different visual features? We addressed this question by comparing observer behavior to that of support vector machine (SVM) models trained on guidance and recognition tasks. Observers searched for a categorically defined teddy bear target in four-object arrays. Target-absent trials consisted of random category distractors rated in their visual similarity to teddy bears. Guidance, quantified as first-fixated objects during search, was strongest for targets, followed by target-similar, medium-similarity, and target-dissimilar distractors. False positive errors to first-fixated distractors also decreased with increasing dissimilarity to the target category. To model guidance, nine teddy bear detectors, using features ranging in biological plausibility, were trained on unblurred bears then tested on blurred versions of the same objects appearing in each search display. Guidance estimates were based on target probabilities obtained from these detectors. To model recognition, nine bear/nonbear classifiers, trained and tested on unblurred objects, were used to classify the object that would be fixated first (based on the detector estimates) as a teddy bear or a distractor. Patterns of categorical guidance and recognition accuracy were modeled almost perfectly by an HMAX model in combination with a color histogram feature. We conclude that guidance and recognition in the context of search are not separate processes mediated by different features, and that what the literature knows as guidance is really recognition performed on blurred objects viewed in the visual periphery.

Modeling guidance and recognition in categorical search: Bridging human and computer object detection

PubMed Central

Zelinsky, Gregory J.; Peng, Yifan; Berg, Alexander C.; Samaras, Dimitris

2013-01-01

Search is commonly described as a repeating cycle of guidance to target-like objects, followed by the recognition of these objects as targets or distractors. Are these indeed separate processes using different visual features? We addressed this question by comparing observer behavior to that of support vector machine (SVM) models trained on guidance and recognition tasks. Observers searched for a categorically defined teddy bear target in four-object arrays. Target-absent trials consisted of random category distractors rated in their visual similarity to teddy bears. Guidance, quantified as first-fixated objects during search, was strongest for targets, followed by target-similar, medium-similarity, and target-dissimilar distractors. False positive errors to first-fixated distractors also decreased with increasing dissimilarity to the target category. To model guidance, nine teddy bear detectors, using features ranging in biological plausibility, were trained on unblurred bears then tested on blurred versions of the same objects appearing in each search display. Guidance estimates were based on target probabilities obtained from these detectors. To model recognition, nine bear/nonbear classifiers, trained and tested on unblurred objects, were used to classify the object that would be fixated first (based on the detector estimates) as a teddy bear or a distractor. Patterns of categorical guidance and recognition accuracy were modeled almost perfectly by an HMAX model in combination with a color histogram feature. We conclude that guidance and recognition in the context of search are not separate processes mediated by different features, and that what the literature knows as guidance is really recognition performed on blurred objects viewed in the visual periphery. PMID:24105460

Optimization of a Multi-Stage ATR System for Small Target Identification

NASA Technical Reports Server (NTRS)

Lin, Tsung-Han; Lu, Thomas; Braun, Henry; Edens, Western; Zhang, Yuhan; Chao, Tien- Hsin; Assad, Christopher; Huntsberger, Terrance

2010-01-01

An Automated Target Recognition system (ATR) was developed to locate and target small object in images and videos. The data is preprocessed and sent to a grayscale optical correlator (GOC) filter to identify possible regionsof- interest (ROIs). Next, features are extracted from ROIs based on Principal Component Analysis (PCA) and sent to neural network (NN) to be classified. The features are analyzed by the NN classifier indicating if each ROI contains the desired target or not. The ATR system was found useful in identifying small boats in open sea. However, due to "noisy background," such as weather conditions, background buildings, or water wakes, some false targets are mis-classified. Feedforward backpropagation and Radial Basis neural networks are optimized for generalization of representative features to reduce false-alarm rate. The neural networks are compared for their performance in classification accuracy, classifying time, and training time.

Aspect-object alignment with Integer Linear Programming in opinion mining.

PubMed

Zhao, Yanyan; Qin, Bing; Liu, Ting; Yang, Wei

2015-01-01

Target extraction is an important task in opinion mining. In this task, a complete target consists of an aspect and its corresponding object. However, previous work has always simply regarded the aspect as the target itself and has ignored the important "object" element. Thus, these studies have addressed incomplete targets, which are of limited use for practical applications. This paper proposes a novel and important sentiment analysis task, termed aspect-object alignment, to solve the "object neglect" problem. The objective of this task is to obtain the correct corresponding object for each aspect. We design a two-step framework for this task. We first provide an aspect-object alignment classifier that incorporates three sets of features, namely, the basic, relational, and special target features. However, the objects that are assigned to aspects in a sentence often contradict each other and possess many complicated features that are difficult to incorporate into a classifier. To resolve these conflicts, we impose two types of constraints in the second step: intra-sentence constraints and inter-sentence constraints. These constraints are encoded as linear formulations, and Integer Linear Programming (ILP) is used as an inference procedure to obtain a final global decision that is consistent with the constraints. Experiments on a corpus in the camera domain demonstrate that the three feature sets used in the aspect-object alignment classifier are effective in improving its performance. Moreover, the classifier with ILP inference performs better than the classifier without it, thereby illustrating that the two types of constraints that we impose are beneficial.

Application of machine learning on brain cancer multiclass classification

NASA Astrophysics Data System (ADS)

Panca, V.; Rustam, Z.

2017-07-01

Classification of brain cancer is a problem of multiclass classification. One approach to solve this problem is by first transforming it into several binary problems. The microarray gene expression dataset has the two main characteristics of medical data: extremely many features (genes) and only a few number of samples. The application of machine learning on microarray gene expression dataset mainly consists of two steps: feature selection and classification. In this paper, the features are selected using a method based on support vector machine recursive feature elimination (SVM-RFE) principle which is improved to solve multiclass classification, called multiple multiclass SVM-RFE. Instead of using only the selected features on a single classifier, this method combines the result of multiple classifiers. The features are divided into subsets and SVM-RFE is used on each subset. Then, the selected features on each subset are put on separate classifiers. This method enhances the feature selection ability of each single SVM-RFE. Twin support vector machine (TWSVM) is used as the method of the classifier to reduce computational complexity. While ordinary SVM finds single optimum hyperplane, the main objective Twin SVM is to find two non-parallel optimum hyperplanes. The experiment on the brain cancer microarray gene expression dataset shows this method could classify 71,4% of the overall test data correctly, using 100 and 1000 genes selected from multiple multiclass SVM-RFE feature selection method. Furthermore, the per class results show that this method could classify data of normal and MD class with 100% accuracy.

Visual feature extraction and establishment of visual tags in the intelligent visual internet of things

NASA Astrophysics Data System (ADS)

Zhao, Yiqun; Wang, Zhihui

2015-12-01

The Internet of things (IOT) is a kind of intelligent networks which can be used to locate, track, identify and supervise people and objects. One of important core technologies of intelligent visual internet of things ( IVIOT) is the intelligent visual tag system. In this paper, a research is done into visual feature extraction and establishment of visual tags of the human face based on ORL face database. Firstly, we use the principal component analysis (PCA) algorithm for face feature extraction, then adopt the support vector machine (SVM) for classifying and face recognition, finally establish a visual tag for face which is already classified. We conducted a experiment focused on a group of people face images, the result show that the proposed algorithm have good performance, and can show the visual tag of objects conveniently.

Remote sensing and reflectance profiling in entomology

USDA-ARS?s Scientific Manuscript database

Remote sensing is about characterizing the status of objects and/or classifies their identity based on a combination of spectral features extracted from reflectance or transmission profiles of radiometric energy. Remote sensing can be ground-based, and therefore acquired at a high spatial resolutio...

Higher criticism thresholding: Optimal feature selection when useful features are rare and weak.

PubMed

Donoho, David; Jin, Jiashun

2008-09-30

In important application fields today-genomics and proteomics are examples-selecting a small subset of useful features is crucial for success of Linear Classification Analysis. We study feature selection by thresholding of feature Z-scores and introduce a principle of threshold selection, based on the notion of higher criticism (HC). For i = 1, 2, ..., p, let pi(i) denote the two-sided P-value associated with the ith feature Z-score and pi((i)) denote the ith order statistic of the collection of P-values. The HC threshold is the absolute Z-score corresponding to the P-value maximizing the HC objective (i/p - pi((i)))/sqrt{i/p(1-i/p)}. We consider a rare/weak (RW) feature model, where the fraction of useful features is small and the useful features are each too weak to be of much use on their own. HC thresholding (HCT) has interesting behavior in this setting, with an intimate link between maximizing the HC objective and minimizing the error rate of the designed classifier, and very different behavior from popular threshold selection procedures such as false discovery rate thresholding (FDRT). In the most challenging RW settings, HCT uses an unconventionally low threshold; this keeps the missed-feature detection rate under better control than FDRT and yields a classifier with improved misclassification performance. Replacing cross-validated threshold selection in the popular Shrunken Centroid classifier with the computationally less expensive and simpler HCT reduces the variance of the selected threshold and the error rate of the constructed classifier. Results on standard real datasets and in asymptotic theory confirm the advantages of HCT.

Higher criticism thresholding: Optimal feature selection when useful features are rare and weak

PubMed Central

Donoho, David; Jin, Jiashun

2008-01-01

In important application fields today—genomics and proteomics are examples—selecting a small subset of useful features is crucial for success of Linear Classification Analysis. We study feature selection by thresholding of feature Z-scores and introduce a principle of threshold selection, based on the notion of higher criticism (HC). For i = 1, 2, …, p, let πi denote the two-sided P-value associated with the ith feature Z-score and π(i) denote the ith order statistic of the collection of P-values. The HC threshold is the absolute Z-score corresponding to the P-value maximizing the HC objective (i/p − π(i))/i/p(1−i/p). We consider a rare/weak (RW) feature model, where the fraction of useful features is small and the useful features are each too weak to be of much use on their own. HC thresholding (HCT) has interesting behavior in this setting, with an intimate link between maximizing the HC objective and minimizing the error rate of the designed classifier, and very different behavior from popular threshold selection procedures such as false discovery rate thresholding (FDRT). In the most challenging RW settings, HCT uses an unconventionally low threshold; this keeps the missed-feature detection rate under better control than FDRT and yields a classifier with improved misclassification performance. Replacing cross-validated threshold selection in the popular Shrunken Centroid classifier with the computationally less expensive and simpler HCT reduces the variance of the selected threshold and the error rate of the constructed classifier. Results on standard real datasets and in asymptotic theory confirm the advantages of HCT. PMID:18815365

Recognition of Simple 3D Geometrical Objects under Partial Occlusion

NASA Astrophysics Data System (ADS)

Barchunova, Alexandra; Sommer, Gerald

In this paper we present a novel procedure for contour-based recognition of partially occluded three-dimensional objects. In our approach we use images of real and rendered objects whose contours have been deformed by a restricted change of the viewpoint. The preparatory part consists of contour extraction, preprocessing, local structure analysis and feature extraction. The main part deals with an extended construction and functionality of the classifier ensemble Adaptive Occlusion Classifier (AOC). It relies on a hierarchical fragmenting algorithm to perform a local structure analysis which is essential when dealing with occlusions. In the experimental part of this paper we present classification results for five classes of simple geometrical figures: prism, cylinder, half cylinder, a cube, and a bridge. We compare classification results for three classical feature extractors: Fourier descriptors, pseudo Zernike and Zernike moments.

Multiple-Primitives Hierarchical Classification of Airborne Laser Scanning Data in Urban Areas

NASA Astrophysics Data System (ADS)

Ni, H.; Lin, X. G.; Zhang, J. X.

2017-09-01

A hierarchical classification method for Airborne Laser Scanning (ALS) data of urban areas is proposed in this paper. This method is composed of three stages among which three types of primitives are utilized, i.e., smooth surface, rough surface, and individual point. In the first stage, the input ALS data is divided into smooth surfaces and rough surfaces by employing a step-wise point cloud segmentation method. In the second stage, classification based on smooth surfaces and rough surfaces is performed. Points in the smooth surfaces are first classified into ground and buildings based on semantic rules. Next, features of rough surfaces are extracted. Then, points in rough surfaces are classified into vegetation and vehicles based on the derived features and Random Forests (RF). In the third stage, point-based features are extracted for the ground points, and then, an individual point classification procedure is performed to classify the ground points into bare land, artificial ground and greenbelt. Moreover, the shortages of the existing studies are analyzed, and experiments show that the proposed method overcomes these shortages and handles more types of objects.

Novel Mahalanobis-based feature selection improves one-class classification of early hepatocellular carcinoma.

PubMed

Thomaz, Ricardo de Lima; Carneiro, Pedro Cunha; Bonin, João Eliton; Macedo, Túlio Augusto Alves; Patrocinio, Ana Claudia; Soares, Alcimar Barbosa

2018-05-01

Detection of early hepatocellular carcinoma (HCC) is responsible for increasing survival rates in up to 40%. One-class classifiers can be used for modeling early HCC in multidetector computed tomography (MDCT), but demand the specific knowledge pertaining to the set of features that best describes the target class. Although the literature outlines several features for characterizing liver lesions, it is unclear which is most relevant for describing early HCC. In this paper, we introduce an unconstrained GA feature selection algorithm based on a multi-objective Mahalanobis fitness function to improve the classification performance for early HCC. We compared our approach to a constrained Mahalanobis function and two other unconstrained functions using Welch's t-test and Gaussian Data Descriptors. The performance of each fitness function was evaluated by cross-validating a one-class SVM. The results show that the proposed multi-objective Mahalanobis fitness function is capable of significantly reducing data dimensionality (96.4%) and improving one-class classification of early HCC (0.84 AUC). Furthermore, the results provide strong evidence that intensity features extracted at the arterial to portal and arterial to equilibrium phases are important for classifying early HCC.

How Can Dolphins Recognize Fish According to Their Echoes? A Statistical Analysis of Fish Echoes

PubMed Central

Yovel, Yossi; Au, Whitlow W. L.

2010-01-01

Echo-based object classification is a fundamental task of animals that use a biosonar system. Dolphins and porpoises should be able to rely on echoes to discriminate a predator from a prey or to select a desired prey from an undesired object. Many studies have shown that dolphins and porpoises can discriminate between objects according to their echoes. All of these studies however, used unnatural objects that can be easily characterized in human terminologies (e.g., metallic spheres, disks, cylinders). In this work, we collected real fish echoes from many angles of acquisition using a sonar system that mimics the emission properties of dolphins and porpoises. We then tested two alternative statistical approaches in classifying these echoes. Our results suggest that fish species can be classified according to echoes returning from porpoise- and dolphin-like signals. These results suggest how dolphins and porpoises can classify fish based on their echoes and provide some insight as to which features might enable the classification. PMID:21124908

How can dolphins recognize fish according to their echoes? A statistical analysis of fish echoes.

PubMed

Yovel, Yossi; Au, Whitlow W L

2010-11-19

Echo-based object classification is a fundamental task of animals that use a biosonar system. Dolphins and porpoises should be able to rely on echoes to discriminate a predator from a prey or to select a desired prey from an undesired object. Many studies have shown that dolphins and porpoises can discriminate between objects according to their echoes. All of these studies however, used unnatural objects that can be easily characterized in human terminologies (e.g., metallic spheres, disks, cylinders). In this work, we collected real fish echoes from many angles of acquisition using a sonar system that mimics the emission properties of dolphins and porpoises. We then tested two alternative statistical approaches in classifying these echoes. Our results suggest that fish species can be classified according to echoes returning from porpoise- and dolphin-like signals. These results suggest how dolphins and porpoises can classify fish based on their echoes and provide some insight as to which features might enable the classification.

Centre-based restricted nearest feature plane with angle classifier for face recognition

NASA Astrophysics Data System (ADS)

Tang, Linlin; Lu, Huifen; Zhao, Liang; Li, Zuohua

2017-10-01

An improved classifier based on the nearest feature plane (NFP), called the centre-based restricted nearest feature plane with the angle (RNFPA) classifier, is proposed for the face recognition problems here. The famous NFP uses the geometrical information of samples to increase the number of training samples, but it increases the computation complexity and it also has an inaccuracy problem coursed by the extended feature plane. To solve the above problems, RNFPA exploits a centre-based feature plane and utilizes a threshold of angle to restrict extended feature space. By choosing the appropriate angle threshold, RNFPA can improve the performance and decrease computation complexity. Experiments in the AT&T face database, AR face database and FERET face database are used to evaluate the proposed classifier. Compared with the original NFP classifier, the nearest feature line (NFL) classifier, the nearest neighbour (NN) classifier and some other improved NFP classifiers, the proposed one achieves competitive performance.

Statistical analysis of textural features for improved classification of oral histopathological images.

PubMed

Muthu Rama Krishnan, M; Shah, Pratik; Chakraborty, Chandan; Ray, Ajoy K

2012-04-01

The objective of this paper is to provide an improved technique, which can assist oncopathologists in correct screening of oral precancerous conditions specially oral submucous fibrosis (OSF) with significant accuracy on the basis of collagen fibres in the sub-epithelial connective tissue. The proposed scheme is composed of collagen fibres segmentation, its textural feature extraction and selection, screening perfomance enhancement under Gaussian transformation and finally classification. In this study, collagen fibres are segmented on R,G,B color channels using back-probagation neural network from 60 normal and 59 OSF histological images followed by histogram specification for reducing the stain intensity variation. Henceforth, textural features of collgen area are extracted using fractal approaches viz., differential box counting and brownian motion curve . Feature selection is done using Kullback-Leibler (KL) divergence criterion and the screening performance is evaluated based on various statistical tests to conform Gaussian nature. Here, the screening performance is enhanced under Gaussian transformation of the non-Gaussian features using hybrid distribution. Moreover, the routine screening is designed based on two statistical classifiers viz., Bayesian classification and support vector machines (SVM) to classify normal and OSF. It is observed that SVM with linear kernel function provides better classification accuracy (91.64%) as compared to Bayesian classifier. The addition of fractal features of collagen under Gaussian transformation improves Bayesian classifier's performance from 80.69% to 90.75%. Results are here studied and discussed.

Computing multiple aggregation levels and contextual features for road facilities recognition using mobile laser scanning data

NASA Astrophysics Data System (ADS)

Yang, Bisheng; Dong, Zhen; Liu, Yuan; Liang, Fuxun; Wang, Yongjun

2017-04-01

In recent years, updating the inventory of road infrastructures based on field work is labor intensive, time consuming, and costly. Fortunately, vehicle-based mobile laser scanning (MLS) systems provide an efficient solution to rapidly capture three-dimensional (3D) point clouds of road environments with high flexibility and precision. However, robust recognition of road facilities from huge volumes of 3D point clouds is still a challenging issue because of complicated and incomplete structures, occlusions and varied point densities. Most existing methods utilize point or object based features to recognize object candidates, and can only extract limited types of objects with a relatively low recognition rate, especially for incomplete and small objects. To overcome these drawbacks, this paper proposes a semantic labeling framework by combing multiple aggregation levels (point-segment-object) of features and contextual features to recognize road facilities, such as road surfaces, road boundaries, buildings, guardrails, street lamps, traffic signs, roadside-trees, power lines, and cars, for highway infrastructure inventory. The proposed method first identifies ground and non-ground points, and extracts road surfaces facilities from ground points. Non-ground points are segmented into individual candidate objects based on the proposed multi-rule region growing method. Then, the multiple aggregation levels of features and the contextual features (relative positions, relative directions, and spatial patterns) associated with each candidate object are calculated and fed into a SVM classifier to label the corresponding candidate object. The recognition performance of combining multiple aggregation levels and contextual features was compared with single level (point, segment, or object) based features using large-scale highway scene point clouds. Comparative studies demonstrated that the proposed semantic labeling framework significantly improves road facilities recognition precision (90.6%) and recall (91.2%), particularly for incomplete and small objects.

Real-time object-to-features vectorisation via Siamese neural networks

NASA Astrophysics Data System (ADS)

Fedorenko, Fedor; Usilin, Sergey

2017-03-01

Object-to-features vectorisation is a hard problem to solve for objects that can be hard to distinguish. Siamese and Triplet neural networks are one of the more recent tools used for such task. However, most networks used are very deep networks that prove to be hard to compute in the Internet of Things setting. In this paper, a computationally efficient neural network is proposed for real-time object-to-features vectorisation into a Euclidean metric space. We use L2 distance to reflect feature vector similarity during both training and testing. In this way, feature vectors we develop can be easily classified using K-Nearest Neighbours classifier. Such approach can be used to train networks to vectorise such "problematic" objects like images of human faces, keypoint image patches, like keypoints on Arctic maps and surrounding marine areas.

Selection of Norway spruce somatic embryos by computer vision

NASA Astrophysics Data System (ADS)

Hamalainen, Jari J.; Jokinen, Kari J.

1993-05-01

A computer vision system was developed for the classification of plant somatic embryos. The embryos are in a Petri dish that is transferred with constant speed and they are recognized as they pass a line scan camera. A classification algorithm needs to be installed for every plant species. This paper describes an algorithm for the recognition of Norway spruce (Picea abies) embryos. A short review of conifer micropropagation by somatic embryogenesis is also given. The recognition algorithm is based on features calculated from the boundary of the object. Only part of the boundary corresponding to the developing cotyledons (2 - 15) and the straight sides of the embryo are used for recognition. An index of the length of the cotyledons describes the developmental stage of the embryo. The testing set for classifier performance consisted of 118 embryos and 478 nonembryos. With the classification tolerances chosen 69% of the objects classified as embryos by a human classifier were selected and 31$% rejected. Less than 1% of the nonembryos were classified as embryos. The basic features developed can probably be easily adapted for the recognition of other conifer somatic embryos.

Automatic stage identification of Drosophila egg chamber based on DAPI images

PubMed Central

Jia, Dongyu; Xu, Qiuping; Xie, Qian; Mio, Washington; Deng, Wu-Min

2016-01-01

The Drosophila egg chamber, whose development is divided into 14 stages, is a well-established model for developmental biology. However, visual stage determination can be a tedious, subjective and time-consuming task prone to errors. Our study presents an objective, reliable and repeatable automated method for quantifying cell features and classifying egg chamber stages based on DAPI images. The proposed approach is composed of two steps: 1) a feature extraction step and 2) a statistical modeling step. The egg chamber features used are egg chamber size, oocyte size, egg chamber ratio and distribution of follicle cells. Methods for determining the on-site of the polytene stage and centripetal migration are also discussed. The statistical model uses linear and ordinal regression to explore the stage-feature relationships and classify egg chamber stages. Combined with machine learning, our method has great potential to enable discovery of hidden developmental mechanisms. PMID:26732176

A Machine Learning Ensemble Classifier for Early Prediction of Diabetic Retinopathy.

PubMed

S K, Somasundaram; P, Alli

2017-11-09

The main complication of diabetes is Diabetic retinopathy (DR), retinal vascular disease and it leads to the blindness. Regular screening for early DR disease detection is considered as an intensive labor and resource oriented task. Therefore, automatic detection of DR diseases is performed only by using the computational technique is the great solution. An automatic method is more reliable to determine the presence of an abnormality in Fundus images (FI) but, the classification process is poorly performed. Recently, few research works have been designed for analyzing texture discrimination capacity in FI to distinguish the healthy images. However, the feature extraction (FE) process was not performed well, due to the high dimensionality. Therefore, to identify retinal features for DR disease diagnosis and early detection using Machine Learning and Ensemble Classification method, called, Machine Learning Bagging Ensemble Classifier (ML-BEC) is designed. The ML-BEC method comprises of two stages. The first stage in ML-BEC method comprises extraction of the candidate objects from Retinal Images (RI). The candidate objects or the features for DR disease diagnosis include blood vessels, optic nerve, neural tissue, neuroretinal rim, optic disc size, thickness and variance. These features are initially extracted by applying Machine Learning technique called, t-distributed Stochastic Neighbor Embedding (t-SNE). Besides, t-SNE generates a probability distribution across high-dimensional images where the images are separated into similar and dissimilar pairs. Then, t-SNE describes a similar probability distribution across the points in the low-dimensional map. This lessens the Kullback-Leibler divergence among two distributions regarding the locations of the points on the map. The second stage comprises of application of ensemble classifiers to the extracted features for providing accurate analysis of digital FI using machine learning. In this stage, an automatic detection of DR screening system using Bagging Ensemble Classifier (BEC) is investigated. With the help of voting the process in ML-BEC, bagging minimizes the error due to variance of the base classifier. With the publicly available retinal image databases, our classifier is trained with 25% of RI. Results show that the ensemble classifier can achieve better classification accuracy (CA) than single classification models. Empirical experiments suggest that the machine learning-based ensemble classifier is efficient for further reducing DR classification time (CT).

Special object extraction from medieval books using superpixels and bag-of-features

NASA Astrophysics Data System (ADS)

Yang, Ying; Rushmeier, Holly

2017-01-01

We propose a method to extract special objects in images of medieval books, which generally represent, for example, figures and capital letters. Instead of working on the single-pixel level, we consider superpixels as the basic classification units for improved time efficiency. More specifically, we classify superpixels into different categories/objects by using a bag-of-features approach, where a superpixel category classifier is trained with the local features of the superpixels of the training images. With the trained classifier, we are able to assign the category labels to the superpixels of a historical document image under test. Finally, special objects can easily be identified and extracted after analyzing the categorization results. Experimental results demonstrate that, as compared to the state-of-the-art algorithms, our method provides comparable performance for some historical books but greatly outperforms them in terms of generality and computational time.

Comparing supervised learning techniques on the task of physical activity recognition.

PubMed

Dalton, A; OLaighin, G

2013-01-01

The objective of this study was to compare the performance of base-level and meta-level classifiers on the task of physical activity recognition. Five wireless kinematic sensors were attached to each subject (n = 25) while they completed a range of basic physical activities in a controlled laboratory setting. Subjects were then asked to carry out similar self-annotated physical activities in a random order and in an unsupervised environment. A combination of time-domain and frequency-domain features were extracted from the sensor data including the first four central moments, zero-crossing rate, average magnitude, sensor cross-correlation, sensor auto-correlation, spectral entropy and dominant frequency components. A reduced feature set was generated using a wrapper subset evaluation technique with a linear forward search and this feature set was employed for classifier comparison. The meta-level classifier AdaBoostM1 with C4.5 Graft as its base-level classifier achieved an overall accuracy of 95%. Equal sized datasets of subject independent data and subject dependent data were used to train this classifier and high recognition rates could be achieved without the need for user specific training. Furthermore, it was found that an accuracy of 88% could be achieved using data from the ankle and wrist sensors only.

Comparison of Object-Based Image Analysis Approaches to Mapping New Buildings in Accra, Ghana Using Multi-Temporal QuickBird Satellite Imagery

PubMed Central

Tsai, Yu Hsin; Stow, Douglas; Weeks, John

2013-01-01

The goal of this study was to map and quantify the number of newly constructed buildings in Accra, Ghana between 2002 and 2010 based on high spatial resolution satellite image data. Two semi-automated feature detection approaches for detecting and mapping newly constructed buildings based on QuickBird very high spatial resolution satellite imagery were analyzed: (1) post-classification comparison; and (2) bi-temporal layerstack classification. Feature Analyst software based on a spatial contextual classifier and ENVI Feature Extraction that uses a true object-based image analysis approach of image segmentation and segment classification were evaluated. Final map products representing new building objects were compared and assessed for accuracy using two object-based accuracy measures, completeness and correctness. The bi-temporal layerstack method generated more accurate results compared to the post-classification comparison method due to less confusion with background objects. The spectral/spatial contextual approach (Feature Analyst) outperformed the true object-based feature delineation approach (ENVI Feature Extraction) due to its ability to more reliably delineate individual buildings of various sizes. Semi-automated, object-based detection followed by manual editing appears to be a reliable and efficient approach for detecting and enumerating new building objects. A bivariate regression analysis was performed using neighborhood-level estimates of new building density regressed on a census-derived measure of socio-economic status, yielding an inverse relationship with R2 = 0.31 (n = 27; p = 0.00). The primary utility of the new building delineation results is to support spatial analyses of land cover and land use and demographic change. PMID:24415810

Object classification for obstacle avoidance

NASA Astrophysics Data System (ADS)

Regensburger, Uwe; Graefe, Volker

1991-03-01

Object recognition is necessary for any mobile robot operating autonomously in the real world. This paper discusses an object classifier based on a 2-D object model. Obstacle candidates are tracked and analyzed false alarms generated by the object detector are recognized and rejected. The methods have been implemented on a multi-processor system and tested in real-world experiments. They work reliably under favorable conditions but sometimes problems occur e. g. when objects contain many features (edges) or move in front of structured background.

Underwater target classification using wavelet packets and neural networks.

PubMed

Azimi-Sadjadi, M R; Yao, D; Huang, Q; Dobeck, G J

2000-01-01

In this paper, a new subband-based classification scheme is developed for classifying underwater mines and mine-like targets from the acoustic backscattered signals. The system consists of a feature extractor using wavelet packets in conjunction with linear predictive coding (LPC), a feature selection scheme, and a backpropagation neural-network classifier. The data set used for this study consists of the backscattered signals from six different objects: two mine-like targets and four nontargets for several aspect angles. Simulation results on ten different noisy realizations and for signal-to-noise ratio (SNR) of 12 dB are presented. The receiver operating characteristic (ROC) curve of the classifier generated based on these results demonstrated excellent classification performance of the system. The generalization ability of the trained network was demonstrated by computing the error and classification rate statistics on a large data set. A multiaspect fusion scheme was also adopted in order to further improve the classification performance.

Enhancing the Performance of LibSVM Classifier by Kernel F-Score Feature Selection

NASA Astrophysics Data System (ADS)

Sarojini, Balakrishnan; Ramaraj, Narayanasamy; Nickolas, Savarimuthu

Medical Data mining is the search for relationships and patterns within the medical datasets that could provide useful knowledge for effective clinical decisions. The inclusion of irrelevant, redundant and noisy features in the process model results in poor predictive accuracy. Much research work in data mining has gone into improving the predictive accuracy of the classifiers by applying the techniques of feature selection. Feature selection in medical data mining is appreciable as the diagnosis of the disease could be done in this patient-care activity with minimum number of significant features. The objective of this work is to show that selecting the more significant features would improve the performance of the classifier. We empirically evaluate the classification effectiveness of LibSVM classifier on the reduced feature subset of diabetes dataset. The evaluations suggest that the feature subset selected improves the predictive accuracy of the classifier and reduce false negatives and false positives.

"Scissors, Paper, Stone": Perceptual Foundations of Noun Classifier Systems.

ERIC Educational Resources Information Center

Erbaugh, Mary S.

While all languages use shape to classify unfamiliar objects, some languages as diverse as Mandarin, Thai, Japanese, Mohawk, and American Sign Language lexicalize these and other types of description as noun classifiers. Classification does not develop from a fixed set of features in the object, but is discourse-sensitive and invoked when it would…

Acoustic signature recognition technique for Human-Object Interactions (HOI) in persistent surveillance systems

NASA Astrophysics Data System (ADS)

Alkilani, Amjad; Shirkhodaie, Amir

2013-05-01

Handling, manipulation, and placement of objects, hereon called Human-Object Interaction (HOI), in the environment generate sounds. Such sounds are readily identifiable by the human hearing. However, in the presence of background environment noises, recognition of minute HOI sounds is challenging, though vital for improvement of multi-modality sensor data fusion in Persistent Surveillance Systems (PSS). Identification of HOI sound signatures can be used as precursors to detection of pertinent threats that otherwise other sensor modalities may miss to detect. In this paper, we present a robust method for detection and classification of HOI events via clustering of extracted features from training of HOI acoustic sound waves. In this approach, salient sound events are preliminary identified and segmented from background via a sound energy tracking method. Upon this segmentation, frequency spectral pattern of each sound event is modeled and its features are extracted to form a feature vector for training. To reduce dimensionality of training feature space, a Principal Component Analysis (PCA) technique is employed to expedite fast classification of test feature vectors, a kd-tree and Random Forest classifiers are trained for rapid classification of training sound waves. Each classifiers employs different similarity distance matching technique for classification. Performance evaluations of classifiers are compared for classification of a batch of training HOI acoustic signatures. Furthermore, to facilitate semantic annotation of acoustic sound events, a scheme based on Transducer Mockup Language (TML) is proposed. The results demonstrate the proposed approach is both reliable and effective, and can be extended to future PSS applications.

Salient object detection based on multi-scale contrast.

PubMed

Wang, Hai; Dai, Lei; Cai, Yingfeng; Sun, Xiaoqiang; Chen, Long

2018-05-01

Due to the development of deep learning networks, a salient object detection based on deep learning networks, which are used to extract the features, has made a great breakthrough compared to the traditional methods. At present, the salient object detection mainly relies on very deep convolutional network, which is used to extract the features. In deep learning networks, an dramatic increase of network depth may cause more training errors instead. In this paper, we use the residual network to increase network depth and to mitigate the errors caused by depth increase simultaneously. Inspired by image simplification, we use color and texture features to obtain simplified image with multiple scales by means of region assimilation on the basis of super-pixels in order to reduce the complexity of images and to improve the accuracy of salient target detection. We refine the feature on pixel level by the multi-scale feature correction method to avoid the feature error when the image is simplified at the above-mentioned region level. The final full connection layer not only integrates features of multi-scale and multi-level but also works as classifier of salient targets. The experimental results show that proposed model achieves better results than other salient object detection models based on original deep learning networks. Copyright © 2018 Elsevier Ltd. All rights reserved.

Approach for Text Classification Based on the Similarity Measurement between Normal Cloud Models

PubMed Central

Dai, Jin; Liu, Xin

2014-01-01

The similarity between objects is the core research area of data mining. In order to reduce the interference of the uncertainty of nature language, a similarity measurement between normal cloud models is adopted to text classification research. On this basis, a novel text classifier based on cloud concept jumping up (CCJU-TC) is proposed. It can efficiently accomplish conversion between qualitative concept and quantitative data. Through the conversion from text set to text information table based on VSM model, the text qualitative concept, which is extraction from the same category, is jumping up as a whole category concept. According to the cloud similarity between the test text and each category concept, the test text is assigned to the most similar category. By the comparison among different text classifiers in different feature selection set, it fully proves that not only does CCJU-TC have a strong ability to adapt to the different text features, but also the classification performance is also better than the traditional classifiers. PMID:24711737

Passive Infrared Thermographic Imaging for Mobile Robot Object Identification

NASA Astrophysics Data System (ADS)

Hinders, M. K.; Fehlman, W. L.

2010-02-01

The usefulness of thermal infrared imaging as a mobile robot sensing modality is explored, and a set of thermal-physical features used to characterize passive thermal objects in outdoor environments is described. Objects that extend laterally beyond the thermal camera's field of view, such as brick walls, hedges, picket fences, and wood walls as well as compact objects that are laterally within the thermal camera's field of view, such as metal poles and tree trunks, are considered. Classification of passive thermal objects is a subtle process since they are not a source for their own emission of thermal energy. A detailed analysis is included of the acquisition and preprocessing of thermal images, as well as the generation and selection of thermal-physical features from these objects within thermal images. Classification performance using these features is discussed, as a precursor to the design of a physics-based model to automatically classify these objects.

Rock classification based on resistivity patterns in electrical borehole wall images

NASA Astrophysics Data System (ADS)

Linek, Margarete; Jungmann, Matthias; Berlage, Thomas; Pechnig, Renate; Clauser, Christoph

2007-06-01

Electrical borehole wall images represent grey-level-coded micro-resistivity measurements at the borehole wall. Different scientific methods have been implemented to transform image data into quantitative log curves. We introduce a pattern recognition technique applying texture analysis, which uses second-order statistics based on studying the occurrence of pixel pairs. We calculate so-called Haralick texture features such as contrast, energy, entropy and homogeneity. The supervised classification method is used for assigning characteristic texture features to different rock classes and assessing the discriminative power of these image features. We use classifiers obtained from training intervals to characterize the entire image data set recovered in ODP hole 1203A. This yields a synthetic lithology profile based on computed texture data. We show that Haralick features accurately classify 89.9% of the training intervals. We obtained misclassification for vesicular basaltic rocks. Hence, further image analysis tools are used to improve the classification reliability. We decompose the 2D image signal by the application of wavelet transformation in order to enhance image objects horizontally, diagonally and vertically. The resulting filtered images are used for further texture analysis. This combined classification based on Haralick features and wavelet transformation improved our classification up to a level of 98%. The application of wavelet transformation increases the consistency between standard logging profiles and texture-derived lithology. Texture analysis of borehole wall images offers the potential to facilitate objective analysis of multiple boreholes with the same lithology.

A shape-based segmentation method for mobile laser scanning point clouds

NASA Astrophysics Data System (ADS)

Yang, Bisheng; Dong, Zhen

2013-07-01

Segmentation of mobile laser point clouds of urban scenes into objects is an important step for post-processing (e.g., interpretation) of point clouds. Point clouds of urban scenes contain numerous objects with significant size variability, complex and incomplete structures, and holes or variable point densities, raising great challenges for the segmentation of mobile laser point clouds. This paper addresses these challenges by proposing a shape-based segmentation method. The proposed method first calculates the optimal neighborhood size of each point to derive the geometric features associated with it, and then classifies the point clouds according to geometric features using support vector machines (SVMs). Second, a set of rules are defined to segment the classified point clouds, and a similarity criterion for segments is proposed to overcome over-segmentation. Finally, the segmentation output is merged based on topological connectivity into a meaningful geometrical abstraction. The proposed method has been tested on point clouds of two urban scenes obtained by different mobile laser scanners. The results show that the proposed method segments large-scale mobile laser point clouds with good accuracy and computationally effective time cost, and that it segments pole-like objects particularly well.

Resident Space Object Characterization and Behavior Understanding via Machine Learning and Ontology-based Bayesian Networks

NASA Astrophysics Data System (ADS)

Furfaro, R.; Linares, R.; Gaylor, D.; Jah, M.; Walls, R.

2016-09-01

In this paper, we present an end-to-end approach that employs machine learning techniques and Ontology-based Bayesian Networks (BN) to characterize the behavior of resident space objects. State-of-the-Art machine learning architectures (e.g. Extreme Learning Machines, Convolutional Deep Networks) are trained on physical models to learn the Resident Space Object (RSO) features in the vectorized energy and momentum states and parameters. The mapping from measurements to vectorized energy and momentum states and parameters enables behavior characterization via clustering in the features space and subsequent RSO classification. Additionally, Space Object Behavioral Ontologies (SOBO) are employed to define and capture the domain knowledge-base (KB) and BNs are constructed from the SOBO in a semi-automatic fashion to execute probabilistic reasoning over conclusions drawn from trained classifiers and/or directly from processed data. Such an approach enables integrating machine learning classifiers and probabilistic reasoning to support higher-level decision making for space domain awareness applications. The innovation here is to use these methods (which have enjoyed great success in other domains) in synergy so that it enables a "from data to discovery" paradigm by facilitating the linkage and fusion of large and disparate sources of information via a Big Data Science and Analytics framework.

Fast object detection algorithm based on HOG and CNN

NASA Astrophysics Data System (ADS)

Lu, Tongwei; Wang, Dandan; Zhang, Yanduo

2018-04-01

In the field of computer vision, object classification and object detection are widely used in many fields. The traditional object detection have two main problems:one is that sliding window of the regional selection strategy is high time complexity and have window redundancy. And the other one is that Robustness of the feature is not well. In order to solve those problems, Regional Proposal Network (RPN) is used to select candidate regions instead of selective search algorithm. Compared with traditional algorithms and selective search algorithms, RPN has higher efficiency and accuracy. We combine HOG feature and convolution neural network (CNN) to extract features. And we use SVM to classify. For TorontoNet, our algorithm's mAP is 1.6 percentage points higher. For OxfordNet, our algorithm's mAP is 1.3 percentage higher.

Integrating visual learning within a model-based ATR system

NASA Astrophysics Data System (ADS)

Carlotto, Mark; Nebrich, Mark

2017-05-01

Automatic target recognition (ATR) systems, like human photo-interpreters, rely on a variety of visual information for detecting, classifying, and identifying manmade objects in aerial imagery. We describe the integration of a visual learning component into the Image Data Conditioner (IDC) for target/clutter and other visual classification tasks. The component is based on an implementation of a model of the visual cortex developed by Serre, Wolf, and Poggio. Visual learning in an ATR context requires the ability to recognize objects independent of location, scale, and rotation. Our method uses IDC to extract, rotate, and scale image chips at candidate target locations. A bootstrap learning method effectively extends the operation of the classifier beyond the training set and provides a measure of confidence. We show how the classifier can be used to learn other features that are difficult to compute from imagery such as target direction, and to assess the performance of the visual learning process itself.

A comparative study for chest radiograph image retrieval using binary texture and deep learning classification.

PubMed

Anavi, Yaron; Kogan, Ilya; Gelbart, Elad; Geva, Ofer; Greenspan, Hayit

2015-08-01

In this work various approaches are investigated for X-ray image retrieval and specifically chest pathology retrieval. Given a query image taken from a data set of 443 images, the objective is to rank images according to similarity. Different features, including binary features, texture features, and deep learning (CNN) features are examined. In addition, two approaches are investigated for the retrieval task. One approach is based on the distance of image descriptors using the above features (hereon termed the "descriptor"-based approach); the second approach ("classification"-based approach) is based on a probability descriptor, generated by a pair-wise classification of each two classes (pathologies) and their decision values using an SVM classifier. Best results are achieved using deep learning features in a classification scheme.

S-CNN: Subcategory-aware convolutional networks for object detection.

PubMed

Chen, Tao; Lu, Shijian; Fan, Jiayuan

2017-09-26

The marriage between the deep convolutional neural network (CNN) and region proposals has made breakthroughs for object detection in recent years. While the discriminative object features are learned via a deep CNN for classification, the large intra-class variation and deformation still limit the performance of the CNN based object detection. We propose a subcategory-aware CNN (S-CNN) to solve the object intra-class variation problem. In the proposed technique, the training samples are first grouped into multiple subcategories automatically through a novel instance sharing maximum margin clustering process. A multi-component Aggregated Channel Feature (ACF) detector is then trained to produce more latent training samples, where each ACF component corresponds to one clustered subcategory. The produced latent samples together with their subcategory labels are further fed into a CNN classifier to filter out false proposals for object detection. An iterative learning algorithm is designed for the joint optimization of image subcategorization, multi-component ACF detector, and subcategory-aware CNN classifier. Experiments on INRIA Person dataset, Pascal VOC 2007 dataset and MS COCO dataset show that the proposed technique clearly outperforms the state-of-the-art methods for generic object detection.

Sequence Based Prediction of Antioxidant Proteins Using a Classifier Selection Strategy

PubMed Central

Zhang, Lina; Zhang, Chengjin; Gao, Rui; Yang, Runtao; Song, Qing

2016-01-01

Antioxidant proteins perform significant functions in maintaining oxidation/antioxidation balance and have potential therapies for some diseases. Accurate identification of antioxidant proteins could contribute to revealing physiological processes of oxidation/antioxidation balance and developing novel antioxidation-based drugs. In this study, an ensemble method is presented to predict antioxidant proteins with hybrid features, incorporating SSI (Secondary Structure Information), PSSM (Position Specific Scoring Matrix), RSA (Relative Solvent Accessibility), and CTD (Composition, Transition, Distribution). The prediction results of the ensemble predictor are determined by an average of prediction results of multiple base classifiers. Based on a classifier selection strategy, we obtain an optimal ensemble classifier composed of RF (Random Forest), SMO (Sequential Minimal Optimization), NNA (Nearest Neighbor Algorithm), and J48 with an accuracy of 0.925. A Relief combined with IFS (Incremental Feature Selection) method is adopted to obtain optimal features from hybrid features. With the optimal features, the ensemble method achieves improved performance with a sensitivity of 0.95, a specificity of 0.93, an accuracy of 0.94, and an MCC (Matthew’s Correlation Coefficient) of 0.880, far better than the existing method. To evaluate the prediction performance objectively, the proposed method is compared with existing methods on the same independent testing dataset. Encouragingly, our method performs better than previous studies. In addition, our method achieves more balanced performance with a sensitivity of 0.878 and a specificity of 0.860. These results suggest that the proposed ensemble method can be a potential candidate for antioxidant protein prediction. For public access, we develop a user-friendly web server for antioxidant protein identification that is freely accessible at http://antioxidant.weka.cc. PMID:27662651

Multimedia Classifier

NASA Astrophysics Data System (ADS)

Costache, G. N.; Gavat, I.

2004-09-01

Along with the aggressive growing of the amount of digital data available (text, audio samples, digital photos and digital movies joined all in the multimedia domain) the need for classification, recognition and retrieval of this kind of data became very important. In this paper will be presented a system structure to handle multimedia data based on a recognition perspective. The main processing steps realized for the interesting multimedia objects are: first, the parameterization, by analysis, in order to obtain a description based on features, forming the parameter vector; second, a classification, generally with a hierarchical structure to make the necessary decisions. For audio signals, both speech and music, the derived perceptual features are the melcepstral (MFCC) and the perceptual linear predictive (PLP) coefficients. For images, the derived features are the geometric parameters of the speaker mouth. The hierarchical classifier consists generally in a clustering stage, based on the Kohonnen Self-Organizing Maps (SOM) and a final stage, based on a powerful classification algorithm called Support Vector Machines (SVM). The system, in specific variants, is applied with good results in two tasks: the first, is a bimodal speech recognition which uses features obtained from speech signal fused to features obtained from speaker's image and the second is a music retrieval from large music database.

Automated Classification of ROSAT Sources Using Heterogeneous Multiwavelength Source Catalogs

NASA Technical Reports Server (NTRS)

McGlynn, Thomas; Suchkov, A. A.; Winter, E. L.; Hanisch, R. J.; White, R. L.; Ochsenbein, F.; Derriere, S.; Voges, W.; Corcoran, M. F.

2004-01-01

We describe an on-line system for automated classification of X-ray sources, ClassX, and present preliminary results of classification of the three major catalogs of ROSAT sources, RASS BSC, RASS FSC, and WGACAT, into six class categories: stars, white dwarfs, X-ray binaries, galaxies, AGNs, and clusters of galaxies. ClassX is based on a machine learning technology. It represents a system of classifiers, each classifier consisting of a considerable number of oblique decision trees. These trees are built as the classifier is 'trained' to recognize various classes of objects using a training sample of sources of known object types. Each source is characterized by a preselected set of parameters, or attributes; the same set is then used as the classifier conducts classification of sources of unknown identity. The ClassX pipeline features an automatic search for X-ray source counterparts among heterogeneous data sets in on-line data archives using Virtual Observatory protocols; it retrieves from those archives all the attributes required by the selected classifier and inputs them to the classifier. The user input to ClassX is typically a file with target coordinates, optionally complemented with target IDs. The output contains the class name, attributes, and class probabilities for all classified targets. We discuss ways to characterize and assess the classifier quality and performance and present the respective validation procedures. Based on both internal and external validation, we conclude that the ClassX classifiers yield reasonable and reliable classifications for ROSAT sources and have the potential to broaden class representation significantly for rare object types.

Blood vessel segmentation in color fundus images based on regional and Hessian features.

PubMed

Shah, Syed Ayaz Ali; Tang, Tong Boon; Faye, Ibrahima; Laude, Augustinus

2017-08-01

To propose a new algorithm of blood vessel segmentation based on regional and Hessian features for image analysis in retinal abnormality diagnosis. Firstly, color fundus images from the publicly available database DRIVE were converted from RGB to grayscale. To enhance the contrast of the dark objects (blood vessels) against the background, the dot product of the grayscale image with itself was generated. To rectify the variation in contrast, we used a 5 × 5 window filter on each pixel. Based on 5 regional features, 1 intensity feature and 2 Hessian features per scale using 9 scales, we extracted a total of 24 features. A linear minimum squared error (LMSE) classifier was trained to classify each pixel into a vessel or non-vessel pixel. The DRIVE dataset provided 20 training and 20 test color fundus images. The proposed algorithm achieves a sensitivity of 72.05% with 94.79% accuracy. Our proposed algorithm achieved higher accuracy (0.9206) at the peripapillary region, where the ocular manifestations in the microvasculature due to glaucoma, central retinal vein occlusion, etc. are most obvious. This supports the proposed algorithm as a strong candidate for automated vessel segmentation.

Comparison of machine learning methods for classifying mediastinal lymph node metastasis of non-small cell lung cancer from 18F-FDG PET/CT images.

PubMed

Wang, Hongkai; Zhou, Zongwei; Li, Yingci; Chen, Zhonghua; Lu, Peiou; Wang, Wenzhi; Liu, Wanyu; Yu, Lijuan

2017-12-01

This study aimed to compare one state-of-the-art deep learning method and four classical machine learning methods for classifying mediastinal lymph node metastasis of non-small cell lung cancer (NSCLC) from 18 F-FDG PET/CT images. Another objective was to compare the discriminative power of the recently popular PET/CT texture features with the widely used diagnostic features such as tumor size, CT value, SUV, image contrast, and intensity standard deviation. The four classical machine learning methods included random forests, support vector machines, adaptive boosting, and artificial neural network. The deep learning method was the convolutional neural networks (CNN). The five methods were evaluated using 1397 lymph nodes collected from PET/CT images of 168 patients, with corresponding pathology analysis results as gold standard. The comparison was conducted using 10 times 10-fold cross-validation based on the criterion of sensitivity, specificity, accuracy (ACC), and area under the ROC curve (AUC). For each classical method, different input features were compared to select the optimal feature set. Based on the optimal feature set, the classical methods were compared with CNN, as well as with human doctors from our institute. For the classical methods, the diagnostic features resulted in 81~85% ACC and 0.87~0.92 AUC, which were significantly higher than the results of texture features. CNN's sensitivity, specificity, ACC, and AUC were 84, 88, 86, and 0.91, respectively. There was no significant difference between the results of CNN and the best classical method. The sensitivity, specificity, and ACC of human doctors were 73, 90, and 82, respectively. All the five machine learning methods had higher sensitivities but lower specificities than human doctors. The present study shows that the performance of CNN is not significantly different from the best classical methods and human doctors for classifying mediastinal lymph node metastasis of NSCLC from PET/CT images. Because CNN does not need tumor segmentation or feature calculation, it is more convenient and more objective than the classical methods. However, CNN does not make use of the import diagnostic features, which have been proved more discriminative than the texture features for classifying small-sized lymph nodes. Therefore, incorporating the diagnostic features into CNN is a promising direction for future research.

Flexible feature-space-construction architecture and its VLSI implementation for multi-scale object detection

NASA Astrophysics Data System (ADS)

Luo, Aiwen; An, Fengwei; Zhang, Xiangyu; Chen, Lei; Huang, Zunkai; Jürgen Mattausch, Hans

2018-04-01

Feature extraction techniques are a cornerstone of object detection in computer-vision-based applications. The detection performance of vison-based detection systems is often degraded by, e.g., changes in the illumination intensity of the light source, foreground-background contrast variations or automatic gain control from the camera. In order to avoid such degradation effects, we present a block-based L1-norm-circuit architecture which is configurable for different image-cell sizes, cell-based feature descriptors and image resolutions according to customization parameters from the circuit input. The incorporated flexibility in both the image resolution and the cell size for multi-scale image pyramids leads to lower computational complexity and power consumption. Additionally, an object-detection prototype for performance evaluation in 65 nm CMOS implements the proposed L1-norm circuit together with a histogram of oriented gradients (HOG) descriptor and a support vector machine (SVM) classifier. The proposed parallel architecture with high hardware efficiency enables real-time processing, high detection robustness, small chip-core area as well as low power consumption for multi-scale object detection.

Biomedical named entity extraction: some issues of corpus compatibilities.

PubMed

Ekbal, Asif; Saha, Sriparna; Sikdar, Utpal Kumar

2013-01-01

Named Entity (NE) extraction is one of the most fundamental and important tasks in biomedical information extraction. It involves identification of certain entities from text and their classification into some predefined categories. In the biomedical community, there is yet no general consensus regarding named entity (NE) annotation; thus, it is very difficult to compare the existing systems due to corpus incompatibilities. Due to this problem we can not also exploit the advantages of using different corpora together. In our present work we address the issues of corpus compatibilities, and use a single objective optimization (SOO) based classifier ensemble technique that uses the search capability of genetic algorithm (GA) for NE extraction in biomedicine. We hypothesize that the reliability of predictions of each classifier differs among the various output classes. We use Conditional Random Field (CRF) and Support Vector Machine (SVM) frameworks to build a number of models depending upon the various representations of the set of features and/or feature templates. It is to be noted that we tried to extract the features without using any deep domain knowledge and/or resources. In order to assess the challenges of corpus compatibilities, we experiment with the different benchmark datasets and their various combinations. Comparison results with the existing approaches prove the efficacy of the used technique. GA based ensemble achieves around 2% performance improvements over the individual classifiers. Degradation in performance on the integrated corpus clearly shows the difficulties of the task. In summary, our used ensemble based approach attains the state-of-the-art performance levels for entity extraction in three different kinds of biomedical datasets. The possible reasons behind the better performance in our used approach are the (i). use of variety and rich features as described in Subsection "Features for named entity extraction"; (ii) use of GA based classifier ensemble technique to combine the outputs of multiple classifiers.

Combining High Spatial Resolution Optical and LIDAR Data for Object-Based Image Classification

NASA Astrophysics Data System (ADS)

Li, R.; Zhang, T.; Geng, R.; Wang, L.

2018-04-01

In order to classify high spatial resolution images more accurately, in this research, a hierarchical rule-based object-based classification framework was developed based on a high-resolution image with airborne Light Detection and Ranging (LiDAR) data. The eCognition software is employed to conduct the whole process. In detail, firstly, the FBSP optimizer (Fuzzy-based Segmentation Parameter) is used to obtain the optimal scale parameters for different land cover types. Then, using the segmented regions as basic units, the classification rules for various land cover types are established according to the spectral, morphological and texture features extracted from the optical images, and the height feature from LiDAR respectively. Thirdly, the object classification results are evaluated by using the confusion matrix, overall accuracy and Kappa coefficients. As a result, a method using the combination of an aerial image and the airborne Lidar data shows higher accuracy.

Classifying the Perceptual Interpretations of a Bistable Image Using EEG and Artificial Neural Networks

PubMed Central

Hramov, Alexander E.; Maksimenko, Vladimir A.; Pchelintseva, Svetlana V.; Runnova, Anastasiya E.; Grubov, Vadim V.; Musatov, Vyacheslav Yu.; Zhuravlev, Maksim O.; Koronovskii, Alexey A.; Pisarchik, Alexander N.

2017-01-01

In order to classify different human brain states related to visual perception of ambiguous images, we use an artificial neural network (ANN) to analyze multichannel EEG. The classifier built on the basis of a multilayer perceptron achieves up to 95% accuracy in classifying EEG patterns corresponding to two different interpretations of the Necker cube. The important feature of our classifier is that trained on one subject it can be used for the classification of EEG traces of other subjects. This result suggests the existence of common features in the EEG structure associated with distinct interpretations of bistable objects. We firmly believe that the significance of our results is not limited to visual perception of the Necker cube images; the proposed experimental approach and developed computational technique based on ANN can also be applied to study and classify different brain states using neurophysiological data recordings. This may give new directions for future research in the field of cognitive and pathological brain activity, and for the development of brain-computer interfaces. PMID:29255403

Classification of visual and linguistic tasks using eye-movement features.

PubMed

Coco, Moreno I; Keller, Frank

2014-03-07

The role of the task has received special attention in visual-cognition research because it can provide causal explanations of goal-directed eye-movement responses. The dependency between visual attention and task suggests that eye movements can be used to classify the task being performed. A recent study by Greene, Liu, and Wolfe (2012), however, fails to achieve accurate classification of visual tasks based on eye-movement features. In the present study, we hypothesize that tasks can be successfully classified when they differ with respect to the involvement of other cognitive domains, such as language processing. We extract the eye-movement features used by Greene et al. as well as additional features from the data of three different tasks: visual search, object naming, and scene description. First, we demonstrated that eye-movement responses make it possible to characterize the goals of these tasks. Then, we trained three different types of classifiers and predicted the task participants performed with an accuracy well above chance (a maximum of 88% for visual search). An analysis of the relative importance of features for classification accuracy reveals that just one feature, i.e., initiation time, is sufficient for above-chance performance (a maximum of 79% accuracy in object naming). Crucially, this feature is independent of task duration, which differs systematically across the three tasks we investigated. Overall, the best task classification performance was obtained with a set of seven features that included both spatial information (e.g., entropy of attention allocation) and temporal components (e.g., total fixation on objects) of the eye-movement record. This result confirms the task-dependent allocation of visual attention and extends previous work by showing that task classification is possible when tasks differ in the cognitive processes involved (purely visual tasks such as search vs. communicative tasks such as scene description).

Mitosis detection using generic features and an ensemble of cascade adaboosts.

PubMed

Tek, F Boray

2013-01-01

Mitosis count is one of the factors that pathologists use to assess the risk of metastasis and survival of the patients, which are affected by the breast cancer. We investigate an application of a set of generic features and an ensemble of cascade adaboosts to the automated mitosis detection. Calculation of the features rely minimally on object-level descriptions and thus require minimal segmentation. The proposed work was developed and tested on International Conference on Pattern Recognition (ICPR) 2012 mitosis detection contest data. We plotted receiver operating characteristics curves of true positive versus false positive rates; calculated recall, precision, F-measure, and region overlap ratio measures. WE TESTED OUR FEATURES WITH TWO DIFFERENT CLASSIFIER CONFIGURATIONS: 1) An ensemble of single adaboosts, 2) an ensemble of cascade adaboosts. On the ICPR 2012 mitosis detection contest evaluation, the cascade ensemble scored 54, 62.7, and 58, whereas the non-cascade version scored 68, 28.1, and 39.7 for the recall, precision, and F-measure measures, respectively. Mostly used features in the adaboost classifier rules were a shape-based feature, which counted granularity and a color-based feature, which relied on Red, Green, and Blue channel statistics. The features, which express the granular structure and color variations, are found useful for mitosis detection. The ensemble of adaboosts performs better than the individual adaboost classifiers. Moreover, the ensemble of cascaded adaboosts was better than the ensemble of single adaboosts for mitosis detection.

Skin lesion computational diagnosis of dermoscopic images: Ensemble models based on input feature manipulation.

PubMed

Oliveira, Roberta B; Pereira, Aledir S; Tavares, João Manuel R S

2017-10-01

The number of deaths worldwide due to melanoma has risen in recent times, in part because melanoma is the most aggressive type of skin cancer. Computational systems have been developed to assist dermatologists in early diagnosis of skin cancer, or even to monitor skin lesions. However, there still remains a challenge to improve classifiers for the diagnosis of such skin lesions. The main objective of this article is to evaluate different ensemble classification models based on input feature manipulation to diagnose skin lesions. Input feature manipulation processes are based on feature subset selections from shape properties, colour variation and texture analysis to generate diversity for the ensemble models. Three subset selection models are presented here: (1) a subset selection model based on specific feature groups, (2) a correlation-based subset selection model, and (3) a subset selection model based on feature selection algorithms. Each ensemble classification model is generated using an optimum-path forest classifier and integrated with a majority voting strategy. The proposed models were applied on a set of 1104 dermoscopic images using a cross-validation procedure. The best results were obtained by the first ensemble classification model that generates a feature subset ensemble based on specific feature groups. The skin lesion diagnosis computational system achieved 94.3% accuracy, 91.8% sensitivity and 96.7% specificity. The input feature manipulation process based on specific feature subsets generated the greatest diversity for the ensemble classification model with very promising results. Copyright © 2017 Elsevier B.V. All rights reserved.

Feature-based RNN target recognition

NASA Astrophysics Data System (ADS)

Bakircioglu, Hakan; Gelenbe, Erol

1998-09-01

Detection and recognition of target signatures in sensory data obtained by synthetic aperture radar (SAR), forward- looking infrared, or laser radar, have received considerable attention in the literature. In this paper, we propose a feature based target classification methodology to detect and classify targets in cluttered SAR images, that makes use of selective signature data from sensory data, together with a neural network technique which uses a set of trained networks based on the Random Neural Network (RNN) model (Gelenbe 89, 90, 91, 93) which is trained to act as a matched filter. We propose and investigate radial features of target shapes that are invariant to rotation, translation, and scale, to characterize target and clutter signatures. These features are then used to train a set of learning RNNs which can be used to detect targets within clutter with high accuracy, and to classify the targets or man-made objects from natural clutter. Experimental data from SAR imagery is used to illustrate and validate the proposed method, and to calculate Receiver Operating Characteristics which illustrate the performance of the proposed algorithm.

An algorithm of adaptive scale object tracking in occlusion

NASA Astrophysics Data System (ADS)

Zhao, Congmei

2017-05-01

Although the correlation filter-based trackers achieve the competitive results both on accuracy and robustness, there are still some problems in handling scale variations, object occlusion, fast motions and so on. In this paper, a multi-scale kernel correlation filter algorithm based on random fern detector was proposed. The tracking task was decomposed into the target scale estimation and the translation estimation. At the same time, the Color Names features and HOG features were fused in response level to further improve the overall tracking performance of the algorithm. In addition, an online random fern classifier was trained to re-obtain the target after the target was lost. By comparing with some algorithms such as KCF, DSST, TLD, MIL, CT and CSK, experimental results show that the proposed approach could estimate the object state accurately and handle the object occlusion effectively.

An AdaBoost Based Approach to Automatic Classification and Detection of Buildings Footprints, Vegetation Areas and Roads from Satellite Images

NASA Astrophysics Data System (ADS)

Gonulalan, Cansu

In recent years, there has been an increasing demand for applications to monitor the targets related to land-use, using remote sensing images. Advances in remote sensing satellites give rise to the research in this area. Many applications ranging from urban growth planning to homeland security have already used the algorithms for automated object recognition from remote sensing imagery. However, they have still problems such as low accuracy on detection of targets, specific algorithms for a specific area etc. In this thesis, we focus on an automatic approach to classify and detect building foot-prints, road networks and vegetation areas. The automatic interpretation of visual data is a comprehensive task in computer vision field. The machine learning approaches improve the capability of classification in an intelligent way. We propose a method, which has high accuracy on detection and classification. The multi class classification is developed for detecting multiple objects. We present an AdaBoost-based approach along with the supervised learning algorithm. The combi- nation of AdaBoost with "Attentional Cascade" is adopted from Viola and Jones [1]. This combination decreases the computation time and gives opportunity to real time applications. For the feature extraction step, our contribution is to combine Haar-like features that include corner, rectangle and Gabor. Among all features, AdaBoost selects only critical features and generates in extremely efficient cascade structured classifier. Finally, we present and evaluate our experimental results. The overall system is tested and high performance of detection is achieved. The precision rate of the final multi-class classifier is over 98%.

An intelligent classifier for prognosis of cardiac resynchronization therapy based on speckle-tracking echocardiograms.

PubMed

Chao, Pei-Kuang; Wang, Chun-Li; Chan, Hsiao-Lung

2012-03-01

Predicting response after cardiac resynchronization therapy (CRT) has been a challenge of cardiologists. About 30% of selected patients based on the standard selection criteria for CRT do not show response after receiving the treatment. This study is aimed to build an intelligent classifier to assist in identifying potential CRT responders by speckle-tracking radial strain based on echocardiograms. The echocardiograms analyzed were acquired before CRT from 26 patients who have received CRT. Sequential forward selection was performed on the parameters obtained by peak-strain timing and phase space reconstruction on speckle-tracking radial strain to find an optimal set of features for creating intelligent classifiers. Support vector machine (SVM) with a linear, quadratic, and polynominal kernel were tested to build classifiers to identify potential responders and non-responders for CRT by selected features. Based on random sub-sampling validation, the best classification performance is correct rate about 95% with 96-97% sensitivity and 93-94% specificity achieved by applying SVM with a quadratic kernel on a set of 3 parameters. The selected 3 parameters contain both indexes extracted by peak-strain timing and phase space reconstruction. An intelligent classifier with an averaged correct rate, sensitivity and specificity above 90% for assisting in identifying CRT responders is built by speckle-tracking radial strain. The classifier can be applied to provide objective suggestion for patient selection of CRT. Copyright © 2011 Elsevier B.V. All rights reserved.

Online Feature Transformation Learning for Cross-Domain Object Category Recognition.

PubMed

Zhang, Xuesong; Zhuang, Yan; Wang, Wei; Pedrycz, Witold

2017-06-09

In this paper, we introduce a new research problem termed online feature transformation learning in the context of multiclass object category recognition. The learning of a feature transformation is viewed as learning a global similarity metric function in an online manner. We first consider the problem of online learning a feature transformation matrix expressed in the original feature space and propose an online passive aggressive feature transformation algorithm. Then these original features are mapped to kernel space and an online single kernel feature transformation (OSKFT) algorithm is developed to learn a nonlinear feature transformation. Based on the OSKFT and the existing Hedge algorithm, a novel online multiple kernel feature transformation algorithm is also proposed, which can further improve the performance of online feature transformation learning in large-scale application. The classifier is trained with k nearest neighbor algorithm together with the learned similarity metric function. Finally, we experimentally examined the effect of setting different parameter values in the proposed algorithms and evaluate the model performance on several multiclass object recognition data sets. The experimental results demonstrate the validity and good performance of our methods on cross-domain and multiclass object recognition application.

Examining the robustness of automated aural classification of active sonar echoes.

PubMed

Murphy, Stefan M; Hines, Paul C

2014-02-01

Active sonar systems are used to detect underwater man-made objects of interest (targets) that are too quiet to be reliably detected with passive sonar. Performance of active sonar can be degraded by false alarms caused by echoes returned from geological seabed structures (clutter) in shallow regions. To reduce false alarms, a method of distinguishing target echoes from clutter echoes is required. Research has demonstrated that perceptual-based signal features similar to those employed in the human auditory system can be used to automatically discriminate between target and clutter echoes, thereby reducing the number of false alarms and improving sonar performance. An active sonar experiment on the Malta Plateau in the Mediterranean Sea was conducted during the Clutter07 sea trial and repeated during the Clutter09 sea trial. The dataset consists of more than 95,000 pulse-compressed echoes returned from two targets and many geological clutter objects. These echoes were processed using an automatic classifier that quantifies the timbre of each echo using a number of perceptual signal features. Using echoes from 2007, the aural classifier was trained to establish a boundary between targets and clutter in the feature space. Temporal robustness was then investigated by testing the classifier on echoes from the 2009 experiment.

Two-dimensional shape classification using generalized Fourier representation and neural networks

NASA Astrophysics Data System (ADS)

Chodorowski, Artur; Gustavsson, Tomas; Mattsson, Ulf

2000-04-01

A shape-based classification method is developed based upon the Generalized Fourier Representation (GFR). GFR can be regarded as an extension of traditional polar Fourier descriptors, suitable for description of closed objects, both convex and concave, with or without holes. Explicit relations of GFR coefficients to regular moments, moment invariants and affine moment invariants are given in the paper. The dual linear relation between GFR coefficients and regular moments was used to compare shape features derive from GFR descriptors and Hu's moment invariants. the GFR was then applied to a clinical problem within oral medicine and used to represent the contours of the lesions in the oral cavity. The lesions studied were leukoplakia and different forms of lichenoid reactions. Shape features were extracted from GFR coefficients in order to classify potentially cancerous oral lesions. Alternative classifiers were investigated based on a multilayer perceptron with different architectures and extensions. The overall classification accuracy for recognition of potentially cancerous oral lesions when using neural network classifier was 85%, while the classification between leukoplakia and reticular lichenoid reactions gave 96% (5-fold cross-validated) recognition rate.

Discovering Fine-grained Sentiment in Suicide Notes

PubMed Central

Wang, Wenbo; Chen, Lu; Tan, Ming; Wang, Shaojun; Sheth, Amit P.

2012-01-01

This paper presents our solution for the i2b2 sentiment classification challenge. Our hybrid system consists of machine learning and rule-based classifiers. For the machine learning classifier, we investigate a variety of lexical, syntactic and knowledge-based features, and show how much these features contribute to the performance of the classifier through experiments. For the rule-based classifier, we propose an algorithm to automatically extract effective syntactic and lexical patterns from training examples. The experimental results show that the rule-based classifier outperforms the baseline machine learning classifier using unigram features. By combining the machine learning classifier and the rule-based classifier, the hybrid system gains a better trade-off between precision and recall, and yields the highest micro-averaged F-measure (0.5038), which is better than the mean (0.4875) and median (0.5027) micro-average F-measures among all participating teams. PMID:22879770

An Ensemble Method with Integration of Feature Selection and Classifier Selection to Detect the Landslides

NASA Astrophysics Data System (ADS)

Zhongqin, G.; Chen, Y.

2017-12-01

Abstract Quickly identify the spatial distribution of landslides automatically is essential for the prevention, mitigation and assessment of the landslide hazard. It's still a challenging job owing to the complicated characteristics and vague boundary of the landslide areas on the image. The high resolution remote sensing image has multi-scales, complex spatial distribution and abundant features, the object-oriented image classification methods can make full use of the above information and thus effectively detect the landslides after the hazard happened. In this research we present a new semi-supervised workflow, taking advantages of recent object-oriented image analysis and machine learning algorithms to quick locate the different origins of landslides of some areas on the southwest part of China. Besides a sequence of image segmentation, feature selection, object classification and error test, this workflow ensemble the feature selection and classifier selection. The feature this study utilized were normalized difference vegetation index (NDVI) change, textural feature derived from the gray level co-occurrence matrices (GLCM), spectral feature and etc. The improvement of this study shows this algorithm significantly removes some redundant feature and the classifiers get fully used. All these improvements lead to a higher accuracy on the determination of the shape of landslides on the high resolution remote sensing image, in particular the flexibility aimed at different kinds of landslides.

Classification of Parkinsonian syndromes from FDG-PET brain data using decision trees with SSM/PCA features.

PubMed

Mudali, D; Teune, L K; Renken, R J; Leenders, K L; Roerdink, J B T M

2015-01-01

Medical imaging techniques like fluorodeoxyglucose positron emission tomography (FDG-PET) have been used to aid in the differential diagnosis of neurodegenerative brain diseases. In this study, the objective is to classify FDG-PET brain scans of subjects with Parkinsonian syndromes (Parkinson's disease, multiple system atrophy, and progressive supranuclear palsy) compared to healthy controls. The scaled subprofile model/principal component analysis (SSM/PCA) method was applied to FDG-PET brain image data to obtain covariance patterns and corresponding subject scores. The latter were used as features for supervised classification by the C4.5 decision tree method. Leave-one-out cross validation was applied to determine classifier performance. We carried out a comparison with other types of classifiers. The big advantage of decision tree classification is that the results are easy to understand by humans. A visual representation of decision trees strongly supports the interpretation process, which is very important in the context of medical diagnosis. Further improvements are suggested based on enlarging the number of the training data, enhancing the decision tree method by bagging, and adding additional features based on (f)MRI data.

Comparison of Genetic Algorithm, Particle Swarm Optimization and Biogeography-based Optimization for Feature Selection to Classify Clusters of Microcalcifications

NASA Astrophysics Data System (ADS)

Khehra, Baljit Singh; Pharwaha, Amar Partap Singh

2017-04-01

Ductal carcinoma in situ (DCIS) is one type of breast cancer. Clusters of microcalcifications (MCCs) are symptoms of DCIS that are recognized by mammography. Selection of robust features vector is the process of selecting an optimal subset of features from a large number of available features in a given problem domain after the feature extraction and before any classification scheme. Feature selection reduces the feature space that improves the performance of classifier and decreases the computational burden imposed by using many features on classifier. Selection of an optimal subset of features from a large number of available features in a given problem domain is a difficult search problem. For n features, the total numbers of possible subsets of features are 2n. Thus, selection of an optimal subset of features problem belongs to the category of NP-hard problems. In this paper, an attempt is made to find the optimal subset of MCCs features from all possible subsets of features using genetic algorithm (GA), particle swarm optimization (PSO) and biogeography-based optimization (BBO). For simulation, a total of 380 benign and malignant MCCs samples have been selected from mammogram images of DDSM database. A total of 50 features extracted from benign and malignant MCCs samples are used in this study. In these algorithms, fitness function is correct classification rate of classifier. Support vector machine is used as a classifier. From experimental results, it is also observed that the performance of PSO-based and BBO-based algorithms to select an optimal subset of features for classifying MCCs as benign or malignant is better as compared to GA-based algorithm.

Taxonomy of multi-focal nematode image stacks by a CNN based image fusion approach.

PubMed

Liu, Min; Wang, Xueping; Zhang, Hongzhong

2018-03-01

In the biomedical field, digital multi-focal images are very important for documentation and communication of specimen data, because the morphological information for a transparent specimen can be captured in form of a stack of high-quality images. Given biomedical image stacks containing multi-focal images, how to efficiently extract effective features from all layers to classify the image stacks is still an open question. We present to use a deep convolutional neural network (CNN) image fusion based multilinear approach for the taxonomy of multi-focal image stacks. A deep CNN based image fusion technique is used to combine relevant information of multi-focal images within a given image stack into a single image, which is more informative and complete than any single image in the given stack. Besides, multi-focal images within a stack are fused along 3 orthogonal directions, and multiple features extracted from the fused images along different directions are combined by canonical correlation analysis (CCA). Because multi-focal image stacks represent the effect of different factors - texture, shape, different instances within the same class and different classes of objects, we embed the deep CNN based image fusion method within a multilinear framework to propose an image fusion based multilinear classifier. The experimental results on nematode multi-focal image stacks demonstrated that the deep CNN image fusion based multilinear classifier can reach a higher classification rate (95.7%) than that by the previous multilinear based approach (88.7%), even we only use the texture feature instead of the combination of texture and shape features as in the previous work. The proposed deep CNN image fusion based multilinear approach shows great potential in building an automated nematode taxonomy system for nematologists. It is effective to classify multi-focal image stacks. Copyright © 2018 Elsevier B.V. All rights reserved.

Improved semi-supervised online boosting for object tracking

NASA Astrophysics Data System (ADS)

Li, Yicui; Qi, Lin; Tan, Shukun

2016-10-01

The advantage of an online semi-supervised boosting method which takes object tracking problem as a classification problem, is training a binary classifier from labeled and unlabeled examples. Appropriate object features are selected based on real time changes in the object. However, the online semi-supervised boosting method faces one key problem: The traditional self-training using the classification results to update the classifier itself, often leads to drifting or tracking failure, due to the accumulated error during each update of the tracker. To overcome the disadvantages of semi-supervised online boosting based on object tracking methods, the contribution of this paper is an improved online semi-supervised boosting method, in which the learning process is guided by positive (P) and negative (N) constraints, termed P-N constraints, which restrict the labeling of the unlabeled samples. First, we train the classification by an online semi-supervised boosting. Then, this classification is used to process the next frame. Finally, the classification is analyzed by the P-N constraints, which are used to verify if the labels of unlabeled data assigned by the classifier are in line with the assumptions made about positive and negative samples. The proposed algorithm can effectively improve the discriminative ability of the classifier and significantly alleviate the drifting problem in tracking applications. In the experiments, we demonstrate real-time tracking of our tracker on several challenging test sequences where our tracker outperforms other related on-line tracking methods and achieves promising tracking performance.

Bladder cancer treatment response assessment with radiomic, clinical, and radiologist semantic features

NASA Astrophysics Data System (ADS)

Gordon, Marshall N.; Cha, Kenny H.; Hadjiiski, Lubomir M.; Chan, Heang-Ping; Cohan, Richard H.; Caoili, Elaine M.; Paramagul, Chintana; Alva, Ajjai; Weizer, Alon Z.

2018-02-01

We are developing a decision support system for assisting clinicians in assessment of response to neoadjuvant chemotherapy for bladder cancer. Accurate treatment response assessment is crucial for identifying responders and improving quality of life for non-responders. An objective machine learning decision support system may help reduce variability and inaccuracy in treatment response assessment. We developed a predictive model to assess the likelihood that a patient will respond based on image and clinical features. With IRB approval, we retrospectively collected a data set of pre- and post- treatment CT scans along with clinical information from surgical pathology from 98 patients. A linear discriminant analysis (LDA) classifier was used to predict the likelihood that a patient would respond to treatment based on radiomic features extracted from CT urography (CTU), a radiologist's semantic feature, and a clinical feature extracted from surgical and pathology reports. The classification accuracy was evaluated using the area under the ROC curve (AUC) with a leave-one-case-out cross validation. The classification accuracy was compared for the systems based on radiomic features, clinical feature, and radiologist's semantic feature. For the system based on only radiomic features the AUC was 0.75. With the addition of clinical information from examination under anesthesia (EUA) the AUC was improved to 0.78. Our study demonstrated the potential of designing a decision support system to assist in treatment response assessment. The combination of clinical features, radiologist semantic features and CTU radiomic features improved the performance of the classifier and the accuracy of treatment response assessment.

A novel end-to-end classifier using domain transferred deep convolutional neural networks for biomedical images.

PubMed

Pang, Shuchao; Yu, Zhezhou; Orgun, Mehmet A

2017-03-01

Highly accurate classification of biomedical images is an essential task in the clinical diagnosis of numerous medical diseases identified from those images. Traditional image classification methods combined with hand-crafted image feature descriptors and various classifiers are not able to effectively improve the accuracy rate and meet the high requirements of classification of biomedical images. The same also holds true for artificial neural network models directly trained with limited biomedical images used as training data or directly used as a black box to extract the deep features based on another distant dataset. In this study, we propose a highly reliable and accurate end-to-end classifier for all kinds of biomedical images via deep learning and transfer learning. We first apply domain transferred deep convolutional neural network for building a deep model; and then develop an overall deep learning architecture based on the raw pixels of original biomedical images using supervised training. In our model, we do not need the manual design of the feature space, seek an effective feature vector classifier or segment specific detection object and image patches, which are the main technological difficulties in the adoption of traditional image classification methods. Moreover, we do not need to be concerned with whether there are large training sets of annotated biomedical images, affordable parallel computing resources featuring GPUs or long times to wait for training a perfect deep model, which are the main problems to train deep neural networks for biomedical image classification as observed in recent works. With the utilization of a simple data augmentation method and fast convergence speed, our algorithm can achieve the best accuracy rate and outstanding classification ability for biomedical images. We have evaluated our classifier on several well-known public biomedical datasets and compared it with several state-of-the-art approaches. We propose a robust automated end-to-end classifier for biomedical images based on a domain transferred deep convolutional neural network model that shows a highly reliable and accurate performance which has been confirmed on several public biomedical image datasets. Copyright © 2017 Elsevier Ireland Ltd. All rights reserved.

Neural network classification of sweet potato embryos

NASA Astrophysics Data System (ADS)

Molto, Enrique; Harrell, Roy C.

1993-05-01

Somatic embryogenesis is a process that allows for the in vitro propagation of thousands of plants in sub-liter size vessels and has been successfully applied to many significant species. The heterogeneity of maturity and quality of embryos produced with this technique requires sorting to obtain a uniform product. An automated harvester is being developed at the University of Florida to sort embryos in vitro at different stages of maturation in a suspension culture. The system utilizes machine vision to characterize embryo morphology and a fluidic based separation device to isolate embryos associated with a pre-defined, targeted morphology. Two different backpropagation neural networks (BNN) were used to classify embryos based on information extracted from the vision system. One network utilized geometric features such as embryo area, length, and symmetry as inputs. The alternative network utilized polar coordinates of an embryo's perimeter with respect to its centroid as inputs. The performances of both techniques were compared with each other and with an embryo classification method based on linear discriminant analysis (LDA). Similar results were obtained with all three techniques. Classification efficiency was improved by reducing the dimension of the feature vector trough a forward stepwise analysis by LDA. In order to enhance the purity of the sample selected as harvestable, a reject to classify option was introduced in the model and analyzed. The best classifier performances (76% overall correct classifications, 75% harvestable objects properly classified, homogeneity improvement ratio 1.5) were obtained using 8 features in a BNN.

Obscenity detection using haar-like features and Gentle Adaboost classifier.

PubMed

Mustafa, Rashed; Min, Yang; Zhu, Dingju

2014-01-01

Large exposure of skin area of an image is considered obscene. This only fact may lead to many false images having skin-like objects and may not detect those images which have partially exposed skin area but have exposed erotogenic human body parts. This paper presents a novel method for detecting nipples from pornographic image contents. Nipple is considered as an erotogenic organ to identify pornographic contents from images. In this research Gentle Adaboost (GAB) haar-cascade classifier and haar-like features used for ensuring detection accuracy. Skin filter prior to detection made the system more robust. The experiment showed that, considering accuracy, haar-cascade classifier performs well, but in order to satisfy detection time, train-cascade classifier is suitable. To validate the results, we used 1198 positive samples containing nipple objects and 1995 negative images. The detection rates for haar-cascade and train-cascade classifiers are 0.9875 and 0.8429, respectively. The detection time for haar-cascade is 0.162 seconds and is 0.127 seconds for train-cascade classifier.

Unified framework for triaxial accelerometer-based fall event detection and classification using cumulants and hierarchical decision tree classifier.

PubMed

Kambhampati, Satya Samyukta; Singh, Vishal; Manikandan, M Sabarimalai; Ramkumar, Barathram

2015-08-01

In this Letter, the authors present a unified framework for fall event detection and classification using the cumulants extracted from the acceleration (ACC) signals acquired using a single waist-mounted triaxial accelerometer. The main objective of this Letter is to find suitable representative cumulants and classifiers in effectively detecting and classifying different types of fall and non-fall events. It was discovered that the first level of the proposed hierarchical decision tree algorithm implements fall detection using fifth-order cumulants and support vector machine (SVM) classifier. In the second level, the fall event classification algorithm uses the fifth-order cumulants and SVM. Finally, human activity classification is performed using the second-order cumulants and SVM. The detection and classification results are compared with those of the decision tree, naive Bayes, multilayer perceptron and SVM classifiers with different types of time-domain features including the second-, third-, fourth- and fifth-order cumulants and the signal magnitude vector and signal magnitude area. The experimental results demonstrate that the second- and fifth-order cumulant features and SVM classifier can achieve optimal detection and classification rates of above 95%, as well as the lowest false alarm rate of 1.03%.

Combining features from ERP components in single-trial EEG for discriminating four-category visual objects.

PubMed

Wang, Changming; Xiong, Shi; Hu, Xiaoping; Yao, Li; Zhang, Jiacai

2012-10-01

Categorization of images containing visual objects can be successfully recognized using single-trial electroencephalograph (EEG) measured when subjects view images. Previous studies have shown that task-related information contained in event-related potential (ERP) components could discriminate two or three categories of object images. In this study, we investigated whether four categories of objects (human faces, buildings, cats and cars) could be mutually discriminated using single-trial EEG data. Here, the EEG waveforms acquired while subjects were viewing four categories of object images were segmented into several ERP components (P1, N1, P2a and P2b), and then Fisher linear discriminant analysis (Fisher-LDA) was used to classify EEG features extracted from ERP components. Firstly, we compared the classification results using features from single ERP components, and identified that the N1 component achieved the highest classification accuracies. Secondly, we discriminated four categories of objects using combining features from multiple ERP components, and showed that combination of ERP components improved four-category classification accuracies by utilizing the complementarity of discriminative information in ERP components. These findings confirmed that four categories of object images could be discriminated with single-trial EEG and could direct us to select effective EEG features for classifying visual objects.

Feature selection for elderly faller classification based on wearable sensors.

PubMed

Howcroft, Jennifer; Kofman, Jonathan; Lemaire, Edward D

2017-05-30

Wearable sensors can be used to derive numerous gait pattern features for elderly fall risk and faller classification; however, an appropriate feature set is required to avoid high computational costs and the inclusion of irrelevant features. The objectives of this study were to identify and evaluate smaller feature sets for faller classification from large feature sets derived from wearable accelerometer and pressure-sensing insole gait data. A convenience sample of 100 older adults (75.5 ± 6.7 years; 76 non-fallers, 24 fallers based on 6 month retrospective fall occurrence) walked 7.62 m while wearing pressure-sensing insoles and tri-axial accelerometers at the head, pelvis, left and right shanks. Feature selection was performed using correlation-based feature selection (CFS), fast correlation based filter (FCBF), and Relief-F algorithms. Faller classification was performed using multi-layer perceptron neural network, naïve Bayesian, and support vector machine classifiers, with 75:25 single stratified holdout and repeated random sampling. The best performing model was a support vector machine with 78% accuracy, 26% sensitivity, 95% specificity, 0.36 F1 score, and 0.31 MCC and one posterior pelvis accelerometer input feature (left acceleration standard deviation). The second best model achieved better sensitivity (44%) and used a support vector machine with 74% accuracy, 83% specificity, 0.44 F1 score, and 0.29 MCC. This model had ten input features: maximum, mean and standard deviation posterior acceleration; maximum, mean and standard deviation anterior acceleration; mean superior acceleration; and three impulse features. The best multi-sensor model sensitivity (56%) was achieved using posterior pelvis and both shank accelerometers and a naïve Bayesian classifier. The best single-sensor model sensitivity (41%) was achieved using the posterior pelvis accelerometer and a naïve Bayesian classifier. Feature selection provided models with smaller feature sets and improved faller classification compared to faller classification without feature selection. CFS and FCBF provided the best feature subset (one posterior pelvis accelerometer feature) for faller classification. However, better sensitivity was achieved by the second best model based on a Relief-F feature subset with three pressure-sensing insole features and seven head accelerometer features. Feature selection should be considered as an important step in faller classification using wearable sensors.

Featureless classification of light curves

NASA Astrophysics Data System (ADS)

Kügler, S. D.; Gianniotis, N.; Polsterer, K. L.

2015-08-01

In the era of rapidly increasing amounts of time series data, classification of variable objects has become the main objective of time-domain astronomy. Classification of irregularly sampled time series is particularly difficult because the data cannot be represented naturally as a vector which can be directly fed into a classifier. In the literature, various statistical features serve as vector representations. In this work, we represent time series by a density model. The density model captures all the information available, including measurement errors. Hence, we view this model as a generalization to the static features which directly can be derived, e.g. as moments from the density. Similarity between each pair of time series is quantified by the distance between their respective models. Classification is performed on the obtained distance matrix. In the numerical experiments, we use data from the OGLE (Optical Gravitational Lensing Experiment) and ASAS (All Sky Automated Survey) surveys and demonstrate that the proposed representation performs up to par with the best currently used feature-based approaches. The density representation preserves all static information present in the observational data, in contrast to a less-complete description by features. The density representation is an upper boundary in terms of information made available to the classifier. Consequently, the predictive power of the proposed classification depends on the choice of similarity measure and classifier, only. Due to its principled nature, we advocate that this new approach of representing time series has potential in tasks beyond classification, e.g. unsupervised learning.

Real-Time Indoor Scene Description for the Visually Impaired Using Autoencoder Fusion Strategies with Visible Cameras.

PubMed

Malek, Salim; Melgani, Farid; Mekhalfi, Mohamed Lamine; Bazi, Yakoub

2017-11-16

This paper describes three coarse image description strategies, which are meant to promote a rough perception of surrounding objects for visually impaired individuals, with application to indoor spaces. The described algorithms operate on images (grabbed by the user, by means of a chest-mounted camera), and provide in output a list of objects that likely exist in his context across the indoor scene. In this regard, first, different colour, texture, and shape-based feature extractors are generated, followed by a feature learning step by means of AutoEncoder (AE) models. Second, the produced features are fused and fed into a multilabel classifier in order to list the potential objects. The conducted experiments point out that fusing a set of AE-learned features scores higher classification rates with respect to using the features individually. Furthermore, with respect to reference works, our method: (i) yields higher classification accuracies, and (ii) runs (at least four times) faster, which enables a potential full real-time application.

Track Everything: Limiting Prior Knowledge in Online Multi-Object Recognition.

PubMed

Wong, Sebastien C; Stamatescu, Victor; Gatt, Adam; Kearney, David; Lee, Ivan; McDonnell, Mark D

2017-10-01

This paper addresses the problem of online tracking and classification of multiple objects in an image sequence. Our proposed solution is to first track all objects in the scene without relying on object-specific prior knowledge, which in other systems can take the form of hand-crafted features or user-based track initialization. We then classify the tracked objects with a fast-learning image classifier, that is based on a shallow convolutional neural network architecture and demonstrate that object recognition improves when this is combined with object state information from the tracking algorithm. We argue that by transferring the use of prior knowledge from the detection and tracking stages to the classification stage, we can design a robust, general purpose object recognition system with the ability to detect and track a variety of object types. We describe our biologically inspired implementation, which adaptively learns the shape and motion of tracked objects, and apply it to the Neovision2 Tower benchmark data set, which contains multiple object types. An experimental evaluation demonstrates that our approach is competitive with the state-of-the-art video object recognition systems that do make use of object-specific prior knowledge in detection and tracking, while providing additional practical advantages by virtue of its generality.

Object-based classification of global undersea topography and geomorphological features from the SRTM30_PLUS data

NASA Astrophysics Data System (ADS)

Dekavalla, Maria; Argialas, Demetre

2017-07-01

The analysis of undersea topography and geomorphological features provides necessary information to related disciplines and many applications. The development of an automated knowledge-based classification approach of undersea topography and geomorphological features is challenging due to their multi-scale nature. The aim of the study is to develop and evaluate an automated knowledge-based OBIA approach to: i) decompose the global undersea topography to multi-scale regions of distinct morphometric properties, and ii) assign the derived regions to characteristic geomorphological features. First, the global undersea topography was decomposed through the SRTM30_PLUS bathymetry data to the so-called morphometric objects of discrete morphometric properties and spatial scales defined by data-driven methods (local variance graphs and nested means) and multi-scale analysis. The derived morphometric objects were combined with additional relative topographic position information computed with a self-adaptive pattern recognition method (geomorphons), and auxiliary data and were assigned to characteristic undersea geomorphological feature classes through a knowledge base, developed from standard definitions. The decomposition of the SRTM30_PLUS data to morphometric objects was considered successful for the requirements of maximizing intra-object and inter-object heterogeneity, based on the near zero values of the Moran's I and the low values of the weighted variance index. The knowledge-based classification approach was tested for its transferability in six case studies of various tectonic settings and achieved the efficient extraction of 11 undersea geomorphological feature classes. The classification results for the six case studies were compared with the digital global seafloor geomorphic features map (GSFM). The 11 undersea feature classes and their producer's accuracies in respect to the GSFM relevant areas were Basin (95%), Continental Shelf (94.9%), Trough (88.4%), Plateau (78.9%), Continental Slope (76.4%), Trench (71.2%), Abyssal Hill (62.9%), Abyssal Plain (62.4%), Ridge (49.8%), Seamount (48.8%) and Continental Rise (25.4%). The knowledge-based OBIA classification approach was considered transferable since the percentages of spatial and thematic agreement between the most of the classified undersea feature classes and the GSFM exhibited low deviations across the six case studies.

Computer-aided diagnostic system for detection of Hashimoto thyroiditis on ultrasound images from a Polish population.

PubMed

Acharya, U Rajendra; Sree, S Vinitha; Krishnan, M Muthu Rama; Molinari, Filippo; Zieleźnik, Witold; Bardales, Ricardo H; Witkowska, Agnieszka; Suri, Jasjit S

2014-02-01

Computer-aided diagnostic (CAD) techniques aid physicians in better diagnosis of diseases by extracting objective and accurate diagnostic information from medical data. Hashimoto thyroiditis is the most common type of inflammation of the thyroid gland. The inflammation changes the structure of the thyroid tissue, and these changes are reflected as echogenic changes on ultrasound images. In this work, we propose a novel CAD system (a class of systems called ThyroScan) that extracts textural features from a thyroid sonogram and uses them to aid in the detection of Hashimoto thyroiditis. In this paradigm, we extracted grayscale features based on stationary wavelet transform from 232 normal and 294 Hashimoto thyroiditis-affected thyroid ultrasound images obtained from a Polish population. Significant features were selected using a Student t test. The resulting feature vectors were used to build and evaluate the following 4 classifiers using a 10-fold stratified cross-validation technique: support vector machine, decision tree, fuzzy classifier, and K-nearest neighbor. Using 7 significant features that characterized the textural changes in the images, the fuzzy classifier had the highest classification accuracy of 84.6%, sensitivity of 82.8%, specificity of 87.0%, and a positive predictive value of 88.9%. The proposed ThyroScan CAD system uses novel features to noninvasively detect the presence of Hashimoto thyroiditis on ultrasound images. Compared to manual interpretations of ultrasound images, the CAD system offers a more objective interpretation of the nature of the thyroid. The preliminary results presented in this work indicate the possibility of using such a CAD system in a clinical setting after evaluating it with larger databases in multicenter clinical trials.

Classification of yeast cells from image features to evaluate pathogen conditions

NASA Astrophysics Data System (ADS)

van der Putten, Peter; Bertens, Laura; Liu, Jinshuo; Hagen, Ferry; Boekhout, Teun; Verbeek, Fons J.

2007-01-01

Morphometrics from images, image analysis, may reveal differences between classes of objects present in the images. We have performed an image-features-based classification for the pathogenic yeast Cryptococcus neoformans. Building and analyzing image collections from the yeast under different environmental or genetic conditions may help to diagnose a new "unseen" situation. Diagnosis here means that retrieval of the relevant information from the image collection is at hand each time a new "sample" is presented. The basidiomycetous yeast Cryptococcus neoformans can cause infections such as meningitis or pneumonia. The presence of an extra-cellular capsule is known to be related to virulence. This paper reports on the approach towards developing classifiers for detecting potentially more or less virulent cells in a sample, i.e. an image, by using a range of features derived from the shape or density distribution. The classifier can henceforth be used for automating screening and annotating existing image collections. In addition we will present our methods for creating samples, collecting images, image preprocessing, identifying "yeast cells" and creating feature extraction from the images. We compare various expertise based and fully automated methods of feature selection and benchmark a range of classification algorithms and illustrate successful application to this particular domain.

Input Decimated Ensembles

NASA Technical Reports Server (NTRS)

Tumer, Kagan; Oza, Nikunj C.; Clancy, Daniel (Technical Monitor)

2001-01-01

Using an ensemble of classifiers instead of a single classifier has been shown to improve generalization performance in many pattern recognition problems. However, the extent of such improvement depends greatly on the amount of correlation among the errors of the base classifiers. Therefore, reducing those correlations while keeping the classifiers' performance levels high is an important area of research. In this article, we explore input decimation (ID), a method which selects feature subsets for their ability to discriminate among the classes and uses them to decouple the base classifiers. We provide a summary of the theoretical benefits of correlation reduction, along with results of our method on two underwater sonar data sets, three benchmarks from the Probenl/UCI repositories, and two synthetic data sets. The results indicate that input decimated ensembles (IDEs) outperform ensembles whose base classifiers use all the input features; randomly selected subsets of features; and features created using principal components analysis, on a wide range of domains.

Connecting a cognitive architecture to robotic perception

NASA Astrophysics Data System (ADS)

Kurup, Unmesh; Lebiere, Christian; Stentz, Anthony; Hebert, Martial

2012-06-01

We present an integrated architecture in which perception and cognition interact and provide information to each other leading to improved performance in real-world situations. Our system integrates the Felzenswalb et. al. object-detection algorithm with the ACT-R cognitive architecture. The targeted task is to predict and classify pedestrian behavior in a checkpoint scenario, most specifically to discriminate between normal versus checkpoint-avoiding behavior. The Felzenswalb algorithm is a learning-based algorithm for detecting and localizing objects in images. ACT-R is a cognitive architecture that has been successfully used to model human cognition with a high degree of fidelity on tasks ranging from basic decision-making to the control of complex systems such as driving or air traffic control. The Felzenswalb algorithm detects pedestrians in the image and provides ACT-R a set of features based primarily on their locations. ACT-R uses its pattern-matching capabilities, specifically its partial-matching and blending mechanisms, to track objects across multiple images and classify their behavior based on the sequence of observed features. ACT-R also provides feedback to the Felzenswalb algorithm in the form of expected object locations that allow the algorithm to eliminate false-positives and improve its overall performance. This capability is an instance of the benefits pursued in developing a richer interaction between bottom-up perceptual processes and top-down goal-directed cognition. We trained the system on individual behaviors (only one person in the scene) and evaluated its performance across single and multiple behavior sets.

An ensemble-of-classifiers based approach for early diagnosis of Alzheimer's disease: classification using structural features of brain images.

PubMed

Farhan, Saima; Fahiem, Muhammad Abuzar; Tauseef, Huma

2014-01-01

Structural brain imaging is playing a vital role in identification of changes that occur in brain associated with Alzheimer's disease. This paper proposes an automated image processing based approach for the identification of AD from MRI of the brain. The proposed approach is novel in a sense that it has higher specificity/accuracy values despite the use of smaller feature set as compared to existing approaches. Moreover, the proposed approach is capable of identifying AD patients in early stages. The dataset selected consists of 85 age and gender matched individuals from OASIS database. The features selected are volume of GM, WM, and CSF and size of hippocampus. Three different classification models (SVM, MLP, and J48) are used for identification of patients and controls. In addition, an ensemble of classifiers, based on majority voting, is adopted to overcome the error caused by an independent base classifier. Ten-fold cross validation strategy is applied for the evaluation of our scheme. Moreover, to evaluate the performance of proposed approach, individual features and combination of features are fed to individual classifiers and ensemble based classifier. Using size of left hippocampus as feature, the accuracy achieved with ensemble of classifiers is 93.75%, with 100% specificity and 87.5% sensitivity.

a Region-Based Multi-Scale Approach for Object-Based Image Analysis

NASA Astrophysics Data System (ADS)

Kavzoglu, T.; Yildiz Erdemir, M.; Tonbul, H.

2016-06-01

Within the last two decades, object-based image analysis (OBIA) considering objects (i.e. groups of pixels) instead of pixels has gained popularity and attracted increasing interest. The most important stage of the OBIA is image segmentation that groups spectrally similar adjacent pixels considering not only the spectral features but also spatial and textural features. Although there are several parameters (scale, shape, compactness and band weights) to be set by the analyst, scale parameter stands out the most important parameter in segmentation process. Estimating optimal scale parameter is crucially important to increase the classification accuracy that depends on image resolution, image object size and characteristics of the study area. In this study, two scale-selection strategies were implemented in the image segmentation process using pan-sharped Qickbird-2 image. The first strategy estimates optimal scale parameters for the eight sub-regions. For this purpose, the local variance/rate of change (LV-RoC) graphs produced by the ESP-2 tool were analysed to determine fine, moderate and coarse scales for each region. In the second strategy, the image was segmented using the three candidate scale values (fine, moderate, coarse) determined from the LV-RoC graph calculated for whole image. The nearest neighbour classifier was applied in all segmentation experiments and equal number of pixels was randomly selected to calculate accuracy metrics (overall accuracy and kappa coefficient). Comparison of region-based and image-based segmentation was carried out on the classified images and found that region-based multi-scale OBIA produced significantly more accurate results than image-based single-scale OBIA. The difference in classification accuracy reached to 10% in terms of overall accuracy.

Analysis and Recognition of Traditional Chinese Medicine Pulse Based on the Hilbert-Huang Transform and Random Forest in Patients with Coronary Heart Disease

PubMed Central

Wang, Yiqin; Yan, Hanxia; Yan, Jianjun; Yuan, Fengyin; Xu, Zhaoxia; Liu, Guoping; Xu, Wenjie

2015-01-01

Objective. This research provides objective and quantitative parameters of the traditional Chinese medicine (TCM) pulse conditions for distinguishing between patients with the coronary heart disease (CHD) and normal people by using the proposed classification approach based on Hilbert-Huang transform (HHT) and random forest. Methods. The energy and the sample entropy features were extracted by applying the HHT to TCM pulse by treating these pulse signals as time series. By using the random forest classifier, the extracted two types of features and their combination were, respectively, used as input data to establish classification model. Results. Statistical results showed that there were significant differences in the pulse energy and sample entropy between the CHD group and the normal group. Moreover, the energy features, sample entropy features, and their combination were inputted as pulse feature vectors; the corresponding average recognition rates were 84%, 76.35%, and 90.21%, respectively. Conclusion. The proposed approach could be appropriately used to analyze pulses of patients with CHD, which can lay a foundation for research on objective and quantitative criteria on disease diagnosis or Zheng differentiation. PMID:26180536

Analysis and Recognition of Traditional Chinese Medicine Pulse Based on the Hilbert-Huang Transform and Random Forest in Patients with Coronary Heart Disease.

PubMed

Guo, Rui; Wang, Yiqin; Yan, Hanxia; Yan, Jianjun; Yuan, Fengyin; Xu, Zhaoxia; Liu, Guoping; Xu, Wenjie

2015-01-01

Objective. This research provides objective and quantitative parameters of the traditional Chinese medicine (TCM) pulse conditions for distinguishing between patients with the coronary heart disease (CHD) and normal people by using the proposed classification approach based on Hilbert-Huang transform (HHT) and random forest. Methods. The energy and the sample entropy features were extracted by applying the HHT to TCM pulse by treating these pulse signals as time series. By using the random forest classifier, the extracted two types of features and their combination were, respectively, used as input data to establish classification model. Results. Statistical results showed that there were significant differences in the pulse energy and sample entropy between the CHD group and the normal group. Moreover, the energy features, sample entropy features, and their combination were inputted as pulse feature vectors; the corresponding average recognition rates were 84%, 76.35%, and 90.21%, respectively. Conclusion. The proposed approach could be appropriately used to analyze pulses of patients with CHD, which can lay a foundation for research on objective and quantitative criteria on disease diagnosis or Zheng differentiation.

Study on Differentiation Management of Grid Energy Metering Device under High Permeability by Distributed Energy and Smart Grid Technology

NASA Astrophysics Data System (ADS)

Wang, Haiyuan; Huang, Rui; Yang, Maotao; Chen, Hao

2017-12-01

At present, the electric energy metering device is classified according to the amount of electric energy and the degree of importance of the measurement object. The measuring device is also selected according to the characteristics of the traditional metering object.With the continuous development of smart grid, the diversification of measurement objects increasingly appear, the traditional measurement object classification has been unable to meet the new measurement object of personalized, differentiated needs.Withal, this paper constructs the subdivision model based on the object feature-system evaluation, classifies according to the characteristics of the measurement object, and carries on the empirical analysis with some kind of measurement object as the research object.The results show that the model works well and can be used to subdivide the metrological objects into different customer groups, which can be reasonably configured and managed for the metering devices. The research of this paper has effectively improved the economy and rationality of the energy metering device management, and improved the working efficiency.

A Novel Locally Linear KNN Method With Applications to Visual Recognition.

PubMed

Liu, Qingfeng; Liu, Chengjun

2017-09-01

A locally linear K Nearest Neighbor (LLK) method is presented in this paper with applications to robust visual recognition. Specifically, the concept of an ideal representation is first presented, which improves upon the traditional sparse representation in many ways. The objective function based on a host of criteria for sparsity, locality, and reconstruction is then optimized to derive a novel representation, which is an approximation to the ideal representation. The novel representation is further processed by two classifiers, namely, an LLK-based classifier and a locally linear nearest mean-based classifier, for visual recognition. The proposed classifiers are shown to connect to the Bayes decision rule for minimum error. Additional new theoretical analysis is presented, such as the nonnegative constraint, the group regularization, and the computational efficiency of the proposed LLK method. New methods such as a shifted power transformation for improving reliability, a coefficients' truncating method for enhancing generalization, and an improved marginal Fisher analysis method for feature extraction are proposed to further improve visual recognition performance. Extensive experiments are implemented to evaluate the proposed LLK method for robust visual recognition. In particular, eight representative data sets are applied for assessing the performance of the LLK method for various visual recognition applications, such as action recognition, scene recognition, object recognition, and face recognition.

Classification of vegetation types in military region

NASA Astrophysics Data System (ADS)

Gonçalves, Miguel; Silva, Jose Silvestre; Bioucas-Dias, Jose

2015-10-01

In decision-making process regarding planning and execution of military operations, the terrain is a determining factor. Aerial photographs are a source of vital information for the success of an operation in hostile region, namely when the cartographic information behind enemy lines is scarce or non-existent. The objective of present work is the development of a tool capable of processing aerial photos. The methodology implemented starts with feature extraction, followed by the application of an automatic selector of features. The next step, using the k-fold cross validation technique, estimates the input parameters for the following classifiers: Sparse Multinomial Logist Regression (SMLR), K Nearest Neighbor (KNN), Linear Classifier using Principal Component Expansion on the Joint Data (PCLDC) and Multi-Class Support Vector Machine (MSVM). These classifiers were used in two different studies with distinct objectives: discrimination of vegetation's density and identification of vegetation's main components. It was found that the best classifier on the first approach is the Sparse Logistic Multinomial Regression (SMLR). On the second approach, the implemented methodology applied to high resolution images showed that the better performance was achieved by KNN classifier and PCLDC. Comparing the two approaches there is a multiscale issue, in which for different resolutions, the best solution to the problem requires different classifiers and the extraction of different features.

Automated robot-assisted surgical skill evaluation: Predictive analytics approach.

PubMed

Fard, Mahtab J; Ameri, Sattar; Darin Ellis, R; Chinnam, Ratna B; Pandya, Abhilash K; Klein, Michael D

2018-02-01

Surgical skill assessment has predominantly been a subjective task. Recently, technological advances such as robot-assisted surgery have created great opportunities for objective surgical evaluation. In this paper, we introduce a predictive framework for objective skill assessment based on movement trajectory data. Our aim is to build a classification framework to automatically evaluate the performance of surgeons with different levels of expertise. Eight global movement features are extracted from movement trajectory data captured by a da Vinci robot for surgeons with two levels of expertise - novice and expert. Three classification methods - k-nearest neighbours, logistic regression and support vector machines - are applied. The result shows that the proposed framework can classify surgeons' expertise as novice or expert with an accuracy of 82.3% for knot tying and 89.9% for a suturing task. This study demonstrates and evaluates the ability of machine learning methods to automatically classify expert and novice surgeons using global movement features. Copyright © 2017 John Wiley & Sons, Ltd.

Geospatial mapping of Antarctic coastal oasis using geographic object-based image analysis and high resolution satellite imagery

NASA Astrophysics Data System (ADS)

Jawak, Shridhar D.; Luis, Alvarinho J.

2016-04-01

An accurate spatial mapping and characterization of land cover features in cryospheric regions is an essential procedure for many geoscientific studies. A novel semi-automated method was devised by coupling spectral index ratios (SIRs) and geographic object-based image analysis (OBIA) to extract cryospheric geospatial information from very high resolution WorldView 2 (WV-2) satellite imagery. The present study addresses development of multiple rule sets for OBIA-based classification of WV-2 imagery to accurately extract land cover features in the Larsemann Hills, east Antarctica. Multilevel segmentation process was applied to WV-2 image to generate different sizes of geographic image objects corresponding to various land cover features with respect to scale parameter. Several SIRs were applied to geographic objects at different segmentation levels to classify land mass, man-made features, snow/ice, and water bodies. We focus on water body class to identify water areas at the image level, considering their uneven appearance on landmass and ice. The results illustrated that synergetic usage of SIRs and OBIA can provide accurate means to identify land cover classes with an overall classification accuracy of ≍97%. In conclusion, our results suggest that OBIA is a powerful tool for carrying out automatic and semiautomatic analysis for most cryospheric remote-sensing applications, and the synergetic coupling with pixel-based SIRs is found to be a superior method for mining geospatial information.

Remote sensing imagery classification using multi-objective gravitational search algorithm

NASA Astrophysics Data System (ADS)

Zhang, Aizhu; Sun, Genyun; Wang, Zhenjie

2016-10-01

Simultaneous optimization of different validity measures can capture different data characteristics of remote sensing imagery (RSI) and thereby achieving high quality classification results. In this paper, two conflicting cluster validity indices, the Xie-Beni (XB) index and the fuzzy C-means (FCM) (Jm) measure, are integrated with a diversity-enhanced and memory-based multi-objective gravitational search algorithm (DMMOGSA) to present a novel multi-objective optimization based RSI classification method. In this method, the Gabor filter method is firstly implemented to extract texture features of RSI. Then, the texture features are syncretized with the spectral features to construct the spatial-spectral feature space/set of the RSI. Afterwards, cluster of the spectral-spatial feature set is carried out on the basis of the proposed method. To be specific, cluster centers are randomly generated initially. After that, the cluster centers are updated and optimized adaptively by employing the DMMOGSA. Accordingly, a set of non-dominated cluster centers are obtained. Therefore, numbers of image classification results of RSI are produced and users can pick up the most promising one according to their problem requirements. To quantitatively and qualitatively validate the effectiveness of the proposed method, the proposed classification method was applied to classifier two aerial high-resolution remote sensing imageries. The obtained classification results are compared with that produced by two single cluster validity index based and two state-of-the-art multi-objective optimization algorithms based classification results. Comparison results show that the proposed method can achieve more accurate RSI classification.

Comparative Performance Analysis of Support Vector Machine, Random Forest, Logistic Regression and k-Nearest Neighbours in Rainbow Trout (Oncorhynchus Mykiss) Classification Using Image-Based Features

PubMed Central

Císař, Petr; Labbé, Laurent; Souček, Pavel; Pelissier, Pablo; Kerneis, Thierry

2018-01-01

The main aim of this study was to develop a new objective method for evaluating the impacts of different diets on the live fish skin using image-based features. In total, one-hundred and sixty rainbow trout (Oncorhynchus mykiss) were fed either a fish-meal based diet (80 fish) or a 100% plant-based diet (80 fish) and photographed using consumer-grade digital camera. Twenty-three colour features and four texture features were extracted. Four different classification methods were used to evaluate fish diets including Random forest (RF), Support vector machine (SVM), Logistic regression (LR) and k-Nearest neighbours (k-NN). The SVM with radial based kernel provided the best classifier with correct classification rate (CCR) of 82% and Kappa coefficient of 0.65. Although the both LR and RF methods were less accurate than SVM, they achieved good classification with CCR 75% and 70% respectively. The k-NN was the least accurate (40%) classification model. Overall, it can be concluded that consumer-grade digital cameras could be employed as the fast, accurate and non-invasive sensor for classifying rainbow trout based on their diets. Furthermore, these was a close association between image-based features and fish diet received during cultivation. These procedures can be used as non-invasive, accurate and precise approaches for monitoring fish status during the cultivation by evaluating diet’s effects on fish skin. PMID:29596375

Comparative Performance Analysis of Support Vector Machine, Random Forest, Logistic Regression and k-Nearest Neighbours in Rainbow Trout (Oncorhynchus Mykiss) Classification Using Image-Based Features.

PubMed

Saberioon, Mohammadmehdi; Císař, Petr; Labbé, Laurent; Souček, Pavel; Pelissier, Pablo; Kerneis, Thierry

2018-03-29

The main aim of this study was to develop a new objective method for evaluating the impacts of different diets on the live fish skin using image-based features. In total, one-hundred and sixty rainbow trout ( Oncorhynchus mykiss ) were fed either a fish-meal based diet (80 fish) or a 100% plant-based diet (80 fish) and photographed using consumer-grade digital camera. Twenty-three colour features and four texture features were extracted. Four different classification methods were used to evaluate fish diets including Random forest (RF), Support vector machine (SVM), Logistic regression (LR) and k -Nearest neighbours ( k -NN). The SVM with radial based kernel provided the best classifier with correct classification rate (CCR) of 82% and Kappa coefficient of 0.65. Although the both LR and RF methods were less accurate than SVM, they achieved good classification with CCR 75% and 70% respectively. The k -NN was the least accurate (40%) classification model. Overall, it can be concluded that consumer-grade digital cameras could be employed as the fast, accurate and non-invasive sensor for classifying rainbow trout based on their diets. Furthermore, these was a close association between image-based features and fish diet received during cultivation. These procedures can be used as non-invasive, accurate and precise approaches for monitoring fish status during the cultivation by evaluating diet's effects on fish skin.

Vibration Sensor-Based Bearing Fault Diagnosis Using Ellipsoid-ARTMAP and Differential Evolution Algorithms

PubMed Central

Liu, Chang; Wang, Guofeng; Xie, Qinglu; Zhang, Yanchao

2014-01-01

Effective fault classification of rolling element bearings provides an important basis for ensuring safe operation of rotating machinery. In this paper, a novel vibration sensor-based fault diagnosis method using an Ellipsoid-ARTMAP network (EAM) and a differential evolution (DE) algorithm is proposed. The original features are firstly extracted from vibration signals based on wavelet packet decomposition. Then, a minimum-redundancy maximum-relevancy algorithm is introduced to select the most prominent features so as to decrease feature dimensions. Finally, a DE-based EAM (DE-EAM) classifier is constructed to realize the fault diagnosis. The major characteristic of EAM is that the sample distribution of each category is realized by using a hyper-ellipsoid node and smoothing operation algorithm. Therefore, it can depict the decision boundary of disperse samples accurately and effectively avoid over-fitting phenomena. To optimize EAM network parameters, the DE algorithm is presented and two objectives, including both classification accuracy and nodes number, are simultaneously introduced as the fitness functions. Meanwhile, an exponential criterion is proposed to realize final selection of the optimal parameters. To prove the effectiveness of the proposed method, the vibration signals of four types of rolling element bearings under different loads were collected. Moreover, to improve the robustness of the classifier evaluation, a two-fold cross validation scheme is adopted and the order of feature samples is randomly arranged ten times within each fold. The results show that DE-EAM classifier can recognize the fault categories of the rolling element bearings reliably and accurately. PMID:24936949

Evaluation of accelerometer based multi-sensor versus single-sensor activity recognition systems.

PubMed

Gao, Lei; Bourke, A K; Nelson, John

2014-06-01

Physical activity has a positive impact on people's well-being and it had been shown to decrease the occurrence of chronic diseases in the older adult population. To date, a substantial amount of research studies exist, which focus on activity recognition using inertial sensors. Many of these studies adopt a single sensor approach and focus on proposing novel features combined with complex classifiers to improve the overall recognition accuracy. In addition, the implementation of the advanced feature extraction algorithms and the complex classifiers exceed the computing ability of most current wearable sensor platforms. This paper proposes a method to adopt multiple sensors on distributed body locations to overcome this problem. The objective of the proposed system is to achieve higher recognition accuracy with "light-weight" signal processing algorithms, which run on a distributed computing based sensor system comprised of computationally efficient nodes. For analysing and evaluating the multi-sensor system, eight subjects were recruited to perform eight normal scripted activities in different life scenarios, each repeated three times. Thus a total of 192 activities were recorded resulting in 864 separate annotated activity states. The methods for designing such a multi-sensor system required consideration of the following: signal pre-processing algorithms, sampling rate, feature selection and classifier selection. Each has been investigated and the most appropriate approach is selected to achieve a trade-off between recognition accuracy and computing execution time. A comparison of six different systems, which employ single or multiple sensors, is presented. The experimental results illustrate that the proposed multi-sensor system can achieve an overall recognition accuracy of 96.4% by adopting the mean and variance features, using the Decision Tree classifier. The results demonstrate that elaborate classifiers and feature sets are not required to achieve high recognition accuracies on a multi-sensor system. Copyright © 2014 IPEM. Published by Elsevier Ltd. All rights reserved.

Fall Detection Using Smartphone Audio Features.

PubMed

Cheffena, Michael

2016-07-01

An automated fall detection system based on smartphone audio features is developed. The spectrogram, mel frequency cepstral coefficents (MFCCs), linear predictive coding (LPC), and matching pursuit (MP) features of different fall and no-fall sound events are extracted from experimental data. Based on the extracted audio features, four different machine learning classifiers: k-nearest neighbor classifier (k-NN), support vector machine (SVM), least squares method (LSM), and artificial neural network (ANN) are investigated for distinguishing between fall and no-fall events. For each audio feature, the performance of each classifier in terms of sensitivity, specificity, accuracy, and computational complexity is evaluated. The best performance is achieved using spectrogram features with ANN classifier with sensitivity, specificity, and accuracy all above 98%. The classifier also has acceptable computational requirement for training and testing. The system is applicable in home environments where the phone is placed in the vicinity of the user.

A region-based segmentation of tumour from brain CT images using nonlinear support vector machine classifier.

PubMed

Nanthagopal, A Padma; Rajamony, R Sukanesh

2012-07-01

The proposed system provides new textural information for segmenting tumours, efficiently and accurately and with less computational time, from benign and malignant tumour images, especially in smaller dimensions of tumour regions of computed tomography (CT) images. Region-based segmentation of tumour from brain CT image data is an important but time-consuming task performed manually by medical experts. The objective of this work is to segment brain tumour from CT images using combined grey and texture features with new edge features and nonlinear support vector machine (SVM) classifier. The selected optimal features are used to model and train the nonlinear SVM classifier to segment the tumour from computed tomography images and the segmentation accuracies are evaluated for each slice of the tumour image. The method is applied on real data of 80 benign, malignant tumour images. The results are compared with the radiologist labelled ground truth. Quantitative analysis between ground truth and the segmented tumour is presented in terms of segmentation accuracy and the overlap similarity measure dice metric. From the analysis and performance measures such as segmentation accuracy and dice metric, it is inferred that better segmentation accuracy and higher dice metric are achieved with the normalized cut segmentation method than with the fuzzy c-means clustering method.

Subauditory Speech Recognition based on EMG/EPG Signals

NASA Technical Reports Server (NTRS)

Jorgensen, Charles; Lee, Diana Dee; Agabon, Shane; Lau, Sonie (Technical Monitor)

2003-01-01

Sub-vocal electromyogram/electro palatogram (EMG/EPG) signal classification is demonstrated as a method for silent speech recognition. Recorded electrode signals from the larynx and sublingual areas below the jaw are noise filtered and transformed into features using complex dual quad tree wavelet transforms. Feature sets for six sub-vocally pronounced words are trained using a trust region scaled conjugate gradient neural network. Real time signals for previously unseen patterns are classified into categories suitable for primitive control of graphic objects. Feature construction, recognition accuracy and an approach for extension of the technique to a variety of real world application areas are presented.

Recognition of lesion correspondence on two mammographic views: a new method of false-positive reduction for computerized mass detection

NASA Astrophysics Data System (ADS)

Sahiner, Berkman; Petrick, Nicholas; Chan, Heang-Ping; Paquerault, Sophie; Helvie, Mark A.; Hadjiiski, Lubomir M.

2001-07-01

We used the correspondence of detected structures on two views of the same breast for false-positive (FP) reduction in computerized detection of mammographic masses. For each initially detected object on one view, we considered all possible pairings with objects on the other view that fell within a radial band defined by the nipple-to-object distances. We designed a 'correspondence classifier' to classify these pairs as either the same mass (a TP-TP pair) or a mismatch (a TP-FP, FP-TP or FP-FP pair). For each pair, similarity measures of morphological and texture features were derived and used as input features in the correspondence classifier. Two-view mammograms from 94 cases were used as a preliminary data set. Initial detection provided 6.3 FPs/image at 96% sensitivity. Further FP reduction in single view resulted in 1.9 FPs/image at 80% sensitivity and 1.1 FPs/image at 70% sensitivity. By combining single-view detection with the correspondence classifier, detection accuracy improved to 1.5 FPs/image at 80% sensitivity and 0.7 FPs/image at 70% sensitivity. Our preliminary results indicate that the correspondence of geometric, morphological, and textural features of a mass on two different views provides valuable additional information for reducing FPs.

Embedded feature ranking for ensemble MLP classifiers.

PubMed

Windeatt, Terry; Duangsoithong, Rakkrit; Smith, Raymond

2011-06-01

A feature ranking scheme for multilayer perceptron (MLP) ensembles is proposed, along with a stopping criterion based upon the out-of-bootstrap estimate. To solve multi-class problems feature ranking is combined with modified error-correcting output coding. Experimental results on benchmark data demonstrate the versatility of the MLP base classifier in removing irrelevant features.

Suicide Note Sentiment Classification: A Supervised Approach Augmented by Web Data

PubMed Central

Xu, Yan; Wang, Yue; Liu, Jiahua; Tu, Zhuowen; Sun, Jian-Tao; Tsujii, Junichi; Chang, Eric

2012-01-01

Objective: To create a sentiment classification system for the Fifth i2b2/VA Challenge Track 2, which can identify thirteen subjective categories and two objective categories. Design: We developed a hybrid system using Support Vector Machine (SVM) classifiers with augmented training data from the Internet. Our system consists of three types of classification-based systems: the first system uses spanning n-gram features for subjective categories, the second one uses bag-of-n-gram features for objective categories, and the third one uses pattern matching for infrequent or subtle emotion categories. The spanning n-gram features are selected by a feature selection algorithm that leverages emotional corpus from weblogs. Special normalization of objective sentences is generalized with shallow parsing and external web knowledge. We utilize three sources of web data: the weblog of LiveJournal which helps to improve the feature selection, the eBay List which assists in special normalization of information and instructions categories, and the suicide project web which provides unlabeled data with similar properties as suicide notes. Measurements: The performance is evaluated by the overall micro-averaged precision, recall and F-measure. Result: Our system achieved an overall micro-averaged F-measure of 0.59. Happiness_peacefulness had the highest F-measure of 0.81. We were ranked as the second best out of 26 competing teams. Conclusion: Our results indicated that classifying fine-grained sentiments at sentence level is a non-trivial task. It is effective to divide categories into different groups according to their semantic properties. In addition, our system performance benefits from external knowledge extracted from publically available web data of other purposes; performance can be further enhanced when more training data is available. PMID:22879758

Obscenity Detection Using Haar-Like Features and Gentle Adaboost Classifier

PubMed Central

Min, Yang; Zhu, Dingju

2014-01-01

Large exposure of skin area of an image is considered obscene. This only fact may lead to many false images having skin-like objects and may not detect those images which have partially exposed skin area but have exposed erotogenic human body parts. This paper presents a novel method for detecting nipples from pornographic image contents. Nipple is considered as an erotogenic organ to identify pornographic contents from images. In this research Gentle Adaboost (GAB) haar-cascade classifier and haar-like features used for ensuring detection accuracy. Skin filter prior to detection made the system more robust. The experiment showed that, considering accuracy, haar-cascade classifier performs well, but in order to satisfy detection time, train-cascade classifier is suitable. To validate the results, we used 1198 positive samples containing nipple objects and 1995 negative images. The detection rates for haar-cascade and train-cascade classifiers are 0.9875 and 0.8429, respectively. The detection time for haar-cascade is 0.162 seconds and is 0.127 seconds for train-cascade classifier. PMID:25003153

Comparison of two satellite imaging platforms for evaluating quasi-circular vegetation patch in the Yellow River Delta, China

NASA Astrophysics Data System (ADS)

Liu, Qingsheng; Liang, Li; Liu, Gaohuan; Huang, Chong

2017-09-01

Vegetation often exists as patch in arid and semi-arid region throughout the world. Vegetation patch can be effectively monitored by remote sensing images. However, not all satellite platforms are suitable to study quasi-circular vegetation patch. This study compares fine (GF-1) and coarse (CBERS-04) resolution platforms, specifically focusing on the quasicircular vegetation patches in the Yellow River Delta (YRD), China. Vegetation patch features (area, shape) were extracted from GF-1 and CBERS-04 imagery using unsupervised classifier (K-Means) and object-oriented approach (Example-based feature extraction with SVM classifier) in order to analyze vegetation patterns. These features were then compared using vector overlay and differencing, and the Root Mean Squared Error (RMSE) was used to determine if the mapped vegetation patches were significantly different. Regardless of K-Means or Example-based feature extraction with SVM classification, it was found that the area of quasi-circular vegetation patches from visual interpretation from QuickBird image (ground truth data) was greater than that from both of GF-1 and CBERS-04, and the number of patches detected from GF-1 data was more than that of CBERS-04 image. It was seen that without expert's experience and professional training on object-oriented approach, K-Means was better than example-based feature extraction with SVM for detecting the patch. It indicated that CBERS-04 could be used to detect the patch with area of more than 300 m2, but GF-1 data was a sufficient source for patch detection in the YRD. However, in the future, finer resolution platforms such as Worldview are needed to gain more detailed insight on patch structures and components and formation mechanism.

Extraction and classification of 3D objects from volumetric CT data

NASA Astrophysics Data System (ADS)

Song, Samuel M.; Kwon, Junghyun; Ely, Austin; Enyeart, John; Johnson, Chad; Lee, Jongkyu; Kim, Namho; Boyd, Douglas P.

2016-05-01

We propose an Automatic Threat Detection (ATD) algorithm for Explosive Detection System (EDS) using our multistage Segmentation Carving (SC) followed by Support Vector Machine (SVM) classifier. The multi-stage Segmentation and Carving (SC) step extracts all suspect 3-D objects. The feature vector is then constructed for all extracted objects and the feature vector is classified by the Support Vector Machine (SVM) previously learned using a set of ground truth threat and benign objects. The learned SVM classifier has shown to be effective in classification of different types of threat materials. The proposed ATD algorithm robustly deals with CT data that are prone to artifacts due to scatter, beam hardening as well as other systematic idiosyncrasies of the CT data. Furthermore, the proposed ATD algorithm is amenable for including newly emerging threat materials as well as for accommodating data from newly developing sensor technologies. Efficacy of the proposed ATD algorithm with the SVM classifier is demonstrated by the Receiver Operating Characteristics (ROC) curve that relates Probability of Detection (PD) as a function of Probability of False Alarm (PFA). The tests performed using CT data of passenger bags shows excellent performance characteristics.

A Genetic-Based Feature Selection Approach in the Identification of Left/Right Hand Motor Imagery for a Brain-Computer Interface

PubMed Central

Yaacoub, Charles; Mhanna, Georges; Rihana, Sandy

2017-01-01

Electroencephalography is a non-invasive measure of the brain electrical activity generated by millions of neurons. Feature extraction in electroencephalography analysis is a core issue that may lead to accurate brain mental state classification. This paper presents a new feature selection method that improves left/right hand movement identification of a motor imagery brain-computer interface, based on genetic algorithms and artificial neural networks used as classifiers. Raw electroencephalography signals are first preprocessed using appropriate filtering. Feature extraction is carried out afterwards, based on spectral and temporal signal components, and thus a feature vector is constructed. As various features might be inaccurate and mislead the classifier, thus degrading the overall system performance, the proposed approach identifies a subset of features from a large feature space, such that the classifier error rate is reduced. Experimental results show that the proposed method is able to reduce the number of features to as low as 0.5% (i.e., the number of ignored features can reach 99.5%) while improving the accuracy, sensitivity, specificity, and precision of the classifier. PMID:28124985

A Genetic-Based Feature Selection Approach in the Identification of Left/Right Hand Motor Imagery for a Brain-Computer Interface.

PubMed

Yaacoub, Charles; Mhanna, Georges; Rihana, Sandy

2017-01-23

Electroencephalography is a non-invasive measure of the brain electrical activity generated by millions of neurons. Feature extraction in electroencephalography analysis is a core issue that may lead to accurate brain mental state classification. This paper presents a new feature selection method that improves left/right hand movement identification of a motor imagery brain-computer interface, based on genetic algorithms and artificial neural networks used as classifiers. Raw electroencephalography signals are first preprocessed using appropriate filtering. Feature extraction is carried out afterwards, based on spectral and temporal signal components, and thus a feature vector is constructed. As various features might be inaccurate and mislead the classifier, thus degrading the overall system performance, the proposed approach identifies a subset of features from a large feature space, such that the classifier error rate is reduced. Experimental results show that the proposed method is able to reduce the number of features to as low as 0.5% (i.e., the number of ignored features can reach 99.5%) while improving the accuracy, sensitivity, specificity, and precision of the classifier.

Optimizing taxonomic classification of marker-gene amplicon sequences with QIIME 2's q2-feature-classifier plugin.

PubMed

Bokulich, Nicholas A; Kaehler, Benjamin D; Rideout, Jai Ram; Dillon, Matthew; Bolyen, Evan; Knight, Rob; Huttley, Gavin A; Gregory Caporaso, J

2018-05-17

Taxonomic classification of marker-gene sequences is an important step in microbiome analysis. We present q2-feature-classifier ( https://github.com/qiime2/q2-feature-classifier ), a QIIME 2 plugin containing several novel machine-learning and alignment-based methods for taxonomy classification. We evaluated and optimized several commonly used classification methods implemented in QIIME 1 (RDP, BLAST, UCLUST, and SortMeRNA) and several new methods implemented in QIIME 2 (a scikit-learn naive Bayes machine-learning classifier, and alignment-based taxonomy consensus methods based on VSEARCH, and BLAST+) for classification of bacterial 16S rRNA and fungal ITS marker-gene amplicon sequence data. The naive-Bayes, BLAST+-based, and VSEARCH-based classifiers implemented in QIIME 2 meet or exceed the species-level accuracy of other commonly used methods designed for classification of marker gene sequences that were evaluated in this work. These evaluations, based on 19 mock communities and error-free sequence simulations, including classification of simulated "novel" marker-gene sequences, are available in our extensible benchmarking framework, tax-credit ( https://github.com/caporaso-lab/tax-credit-data ). Our results illustrate the importance of parameter tuning for optimizing classifier performance, and we make recommendations regarding parameter choices for these classifiers under a range of standard operating conditions. q2-feature-classifier and tax-credit are both free, open-source, BSD-licensed packages available on GitHub.

Automatic staging of bladder cancer on CT urography

NASA Astrophysics Data System (ADS)

Garapati, Sankeerth S.; Hadjiiski, Lubomir M.; Cha, Kenny H.; Chan, Heang-Ping; Caoili, Elaine M.; Cohan, Richard H.; Weizer, Alon; Alva, Ajjai; Paramagul, Chintana; Wei, Jun; Zhou, Chuan

2016-03-01

Correct staging of bladder cancer is crucial for the decision of neoadjuvant chemotherapy treatment and minimizing the risk of under- or over-treatment. Subjectivity and variability of clinicians in utilizing available diagnostic information may lead to inaccuracy in staging bladder cancer. An objective decision support system that merges the information in a predictive model based on statistical outcomes of previous cases and machine learning may assist clinicians in making more accurate and consistent staging assessments. In this study, we developed a preliminary method to stage bladder cancer. With IRB approval, 42 bladder cancer cases with CTU scans were collected from patient files. The cases were classified into two classes based on pathological stage T2, which is the decision threshold for neoadjuvant chemotherapy treatment (i.e. for stage >=T2) clinically. There were 21 cancers below stage T2 and 21 cancers at stage T2 or above. All 42 lesions were automatically segmented using our auto-initialized cascaded level sets (AI-CALS) method. Morphological features were extracted, which were selected and merged by linear discriminant analysis (LDA) classifier. A leave-one-case-out resampling scheme was used to train and test the classifier using the 42 lesions. The classification accuracy was quantified using the area under the ROC curve (Az). The average training Az was 0.97 and the test Az was 0.85. The classifier consistently selected the lesion volume, a gray level feature and a contrast feature. This predictive model shows promise for assisting in assessing the bladder cancer stage.

Object oriented classification of high resolution data for inventory of horticultural crops

NASA Astrophysics Data System (ADS)

Hebbar, R.; Ravishankar, H. M.; Trivedi, S.; Subramoniam, S. R.; Uday, R.; Dadhwal, V. K.

2014-11-01

High resolution satellite images are associated with large variance and thus, per pixel classifiers often result in poor accuracy especially in delineation of horticultural crops. In this context, object oriented techniques are powerful and promising methods for classification. In the present study, a semi-automatic object oriented feature extraction model has been used for delineation of horticultural fruit and plantation crops using Erdas Objective Imagine. Multi-resolution data from Resourcesat LISS-IV and Cartosat-1 have been used as source data in the feature extraction model. Spectral and textural information along with NDVI were used as inputs for generation of Spectral Feature Probability (SFP) layers using sample training pixels. The SFP layers were then converted into raster objects using threshold and clump function resulting in pixel probability layer. A set of raster and vector operators was employed in the subsequent steps for generating thematic layer in the vector format. This semi-automatic feature extraction model was employed for classification of major fruit and plantations crops viz., mango, banana, citrus, coffee and coconut grown under different agro-climatic conditions. In general, the classification accuracy of about 75-80 per cent was achieved for these crops using object based classification alone and the same was further improved using minimal visual editing of misclassified areas. A comparison of on-screen visual interpretation with object oriented approach showed good agreement. It was observed that old and mature plantations were classified more accurately while young and recently planted ones (3 years or less) showed poor classification accuracy due to mixed spectral signature, wider spacing and poor stands of plantations. The results indicated the potential use of object oriented approach for classification of high resolution data for delineation of horticultural fruit and plantation crops. The present methodology is applicable at local levels and future development is focused on up-scaling the methodology for generation of fruit and plantation crop maps at regional and national level which is important for creation of database for overall horticultural crop development.

Hidden Markov Model and Support Vector Machine based decoding of finger movements using Electrocorticography

PubMed Central

Wissel, Tobias; Pfeiffer, Tim; Frysch, Robert; Knight, Robert T.; Chang, Edward F.; Hinrichs, Hermann; Rieger, Jochem W.; Rose, Georg

2013-01-01

Objective Support Vector Machines (SVM) have developed into a gold standard for accurate classification in Brain-Computer-Interfaces (BCI). The choice of the most appropriate classifier for a particular application depends on several characteristics in addition to decoding accuracy. Here we investigate the implementation of Hidden Markov Models (HMM)for online BCIs and discuss strategies to improve their performance. Approach We compare the SVM, serving as a reference, and HMMs for classifying discrete finger movements obtained from the Electrocorticograms of four subjects doing a finger tapping experiment. The classifier decisions are based on a subset of low-frequency time domain and high gamma oscillation features. Main results We show that decoding optimization between the two approaches is due to the way features are extracted and selected and less dependent on the classifier. An additional gain in HMM performance of up to 6% was obtained by introducing model constraints. Comparable accuracies of up to 90% were achieved with both SVM and HMM with the high gamma cortical response providing the most important decoding information for both techniques. Significance We discuss technical HMM characteristics and adaptations in the context of the presented data as well as for general BCI applications. Our findings suggest that HMMs and their characteristics are promising for efficient online brain-computer interfaces. PMID:24045504

Performance evaluation of object based greenhouse detection from Sentinel-2 MSI and Landsat 8 OLI data: A case study from Almería (Spain)

NASA Astrophysics Data System (ADS)

Novelli, Antonio; Aguilar, Manuel A.; Nemmaoui, Abderrahim; Aguilar, Fernando J.; Tarantino, Eufemia

2016-10-01

This paper shows the first comparison between data from Sentinel-2 (S2) Multi Spectral Instrument (MSI) and Landsat 8 (L8) Operational Land Imager (OLI) headed up to greenhouse detection. Two closely related in time scenes, one for each sensor, were classified by using Object Based Image Analysis and Random Forest (RF). The RF input consisted of several object-based features computed from spectral bands and including mean values, spectral indices and textural features. S2 and L8 data comparisons were also extended using a common segmentation dataset extracted form VHR World-View 2 (WV2) imagery to test differences only due to their specific spectral contribution. The best band combinations to perform segmentation were found through a modified version of the Euclidian Distance 2 index. Four different RF classifications schemes were considered achieving 89.1%, 91.3%, 90.9% and 93.4% as the best overall accuracies respectively, evaluated over the whole study area.

Pathological speech signal analysis and classification using empirical mode decomposition.

PubMed

Kaleem, Muhammad; Ghoraani, Behnaz; Guergachi, Aziz; Krishnan, Sridhar

2013-07-01

Automated classification of normal and pathological speech signals can provide an objective and accurate mechanism for pathological speech diagnosis, and is an active area of research. A large part of this research is based on analysis of acoustic measures extracted from sustained vowels. However, sustained vowels do not reflect real-world attributes of voice as effectively as continuous speech, which can take into account important attributes of speech such as rapid voice onset and termination, changes in voice frequency and amplitude, and sudden discontinuities in speech. This paper presents a methodology based on empirical mode decomposition (EMD) for classification of continuous normal and pathological speech signals obtained from a well-known database. EMD is used to decompose randomly chosen portions of speech signals into intrinsic mode functions, which are then analyzed to extract meaningful temporal and spectral features, including true instantaneous features which can capture discriminative information in signals hidden at local time-scales. A total of six features are extracted, and a linear classifier is used with the feature vector to classify continuous speech portions obtained from a database consisting of 51 normal and 161 pathological speakers. A classification accuracy of 95.7 % is obtained, thus demonstrating the effectiveness of the methodology.

Automated EEG artifact elimination by applying machine learning algorithms to ICA-based features

NASA Astrophysics Data System (ADS)

Radüntz, Thea; Scouten, Jon; Hochmuth, Olaf; Meffert, Beate

2017-08-01

Objective. Biological and non-biological artifacts cause severe problems when dealing with electroencephalogram (EEG) recordings. Independent component analysis (ICA) is a widely used method for eliminating various artifacts from recordings. However, evaluating and classifying the calculated independent components (IC) as artifact or EEG is not fully automated at present. Approach. In this study, we propose a new approach for automated artifact elimination, which applies machine learning algorithms to ICA-based features. Main results. We compared the performance of our classifiers with the visual classification results given by experts. The best result with an accuracy rate of 95% was achieved using features obtained by range filtering of the topoplots and IC power spectra combined with an artificial neural network. Significance. Compared with the existing automated solutions, our proposed method is not limited to specific types of artifacts, electrode configurations, or number of EEG channels. The main advantages of the proposed method is that it provides an automatic, reliable, real-time capable, and practical tool, which avoids the need for the time-consuming manual selection of ICs during artifact removal.

Explosive hazard detection using MIMO forward-looking ground penetrating radar

NASA Astrophysics Data System (ADS)

Shaw, Darren; Ho, K. C.; Stone, Kevin; Keller, James M.; Popescu, Mihail; Anderson, Derek T.; Luke, Robert H.; Burns, Brian

2015-05-01

This paper proposes a machine learning algorithm for subsurface object detection on multiple-input-multiple-output (MIMO) forward-looking ground-penetrating radar (FLGPR). By detecting hazards using FLGPR, standoff distances of up to tens of meters can be acquired, but this is at the degradation of performance due to high false alarm rates. The proposed system utilizes an anomaly detection prescreener to identify potential object locations. Alarm locations have multiple one-dimensional (ML) spectral features, two-dimensional (2D) spectral features, and log-Gabor statistic features extracted. The ability of these features to reduce the number of false alarms and increase the probability of detection is evaluated for both co-polarizations present in the Akela MIMO array. Classification is performed by a Support Vector Machine (SVM) with lane-based cross-validation for training and testing. Class imbalance and optimized SVM kernel parameters are considered during classifier training.

Objective Classification of Radar Profile Types, and Their Relationship to Lightning Occurrence

NASA Technical Reports Server (NTRS)

Boccippio, Dennis

2003-01-01

A cluster analysis technique is used to identify 16 "archetypal" vertical radar profile types from a large, globally representative sample of profiles from the TRMM Precipitation Radar. These include nine convective types (7 of these deep convective) and seven stratiform types (5 of these clearly glaciated). Radar profile classification provides an alternative to conventional deep convective storm metrics, such as 30 dBZ echo height, maximum reflectivity or VIL. As expected, the global frequency of occurrence of deep convective profile types matches satellite-observed total lightning production, including to very small scall local features. Each location's "mix" of profile types provides an objective description of the local convective spectrum, and in turn, is a first step in objectively classifying convective regimes. These classifiers are tested as inputs to a neural network which attempts to predict lightning occurrence based on radar-only storm observations, and performance is compared with networks using traditional radar metrics as inputs.

Feature extraction and classification of clouds in high resolution panchromatic satellite imagery

NASA Astrophysics Data System (ADS)

Sharghi, Elan

The development of sophisticated remote sensing sensors is rapidly increasing, and the vast amount of satellite imagery collected is too much to be analyzed manually by a human image analyst. It has become necessary for a tool to be developed to automate the job of an image analyst. This tool would need to intelligently detect and classify objects of interest through computer vision algorithms. Existing software called the Rapid Image Exploitation Resource (RAPIER®) was designed by engineers at Space and Naval Warfare Systems Center Pacific (SSC PAC) to perform exactly this function. This software automatically searches for anomalies in the ocean and reports the detections as a possible ship object. However, if the image contains a high percentage of cloud coverage, a high number of false positives are triggered by the clouds. The focus of this thesis is to explore various feature extraction and classification methods to accurately distinguish clouds from ship objects. An examination of a texture analysis method, line detection using the Hough transform, and edge detection using wavelets are explored as possible feature extraction methods. The features are then supplied to a K-Nearest Neighbors (KNN) or Support Vector Machine (SVM) classifier. Parameter options for these classifiers are explored and the optimal parameters are determined.

Wide field imaging - I. Applications of neural networks to object detection and star/galaxy classification

NASA Astrophysics Data System (ADS)

Andreon, S.; Gargiulo, G.; Longo, G.; Tagliaferri, R.; Capuano, N.

2000-12-01

Astronomical wide-field imaging performed with new large-format CCD detectors poses data reduction problems of unprecedented scale, which are difficult to deal with using traditional interactive tools. We present here NExt (Neural Extractor), a new neural network (NN) based package capable of detecting objects and performing both deblending and star/galaxy classification in an automatic way. Traditionally, in astronomical images, objects are first distinguished from the noisy background by searching for sets of connected pixels having brightnesses above a given threshold; they are then classified as stars or as galaxies through diagnostic diagrams having variables chosen according to the astronomer's taste and experience. In the extraction step, assuming that images are well sampled, NExt requires only the simplest a priori definition of `what an object is' (i.e. it keeps all structures composed of more than one pixel) and performs the detection via an unsupervised NN, approaching detection as a clustering problem that has been thoroughly studied in the artificial intelligence literature. The first part of the NExt procedure consists of an optimal compression of the redundant information contained in the pixels via a mapping from pixel intensities to a subspace individualized through principal component analysis. At magnitudes fainter than the completeness limit, stars are usually almost indistinguishable from galaxies, and therefore the parameters characterizing the two classes do not lie in disconnected subspaces, thus preventing the use of unsupervised methods. We therefore adopted a supervised NN (i.e. a NN that first finds the rules to classify objects from examples and then applies them to the whole data set). In practice, each object is classified depending on its membership of the regions mapping the input feature space in the training set. In order to obtain an objective and reliable classification, instead of using an arbitrarily defined set of features we use a NN to select the most significant features among the large number of measured ones, and then we use these selected features to perform the classification task. In order to optimize the performance of the system, we implemented and tested several different models of NN. The comparison of the NExt performance with that of the best detection and classification package known to the authors (SExtractor) shows that NExt is at least as effective as the best traditional packages.

A Finger-Shaped Tactile Sensor for Fabric Surfaces Evaluation by 2-Dimensional Active Sliding Touch

PubMed Central

Hu, Haihua; Han, Yezhen; Song, Aiguo; Chen, Shanguang; Wang, Chunhui; Wang, Zheng

2014-01-01

Sliding tactile perception is a basic function for human beings to determine the mechanical properties of object surfaces and recognize materials. Imitating this process, this paper proposes a novel finger-shaped tactile sensor based on a thin piezoelectric polyvinylidene fluoride (PVDF) film for surface texture measurement. A parallelogram mechanism is designed to ensure that the sensor applies a constant contact force perpendicular to the object surface, and a 2-dimensional movable mechanical structure is utilized to generate the relative motion at a certain speed between the sensor and the object surface. By controlling the 2-dimensional motion of the finger-shaped sensor along the object surface, small height/depth variation of surface texture changes the output charge of PVDF film then surface texture can be measured. In this paper, the finger-shaped tactile sensor is used to evaluate and classify five different kinds of linen. Fast Fourier Transformation (FFT) is utilized to get original attribute data of surface in the frequency domain, and principal component analysis (PCA) is used to compress the attribute data and extract feature information. Finally, low dimensional features are classified by Support Vector Machine (SVM). The experimental results show that this finger-shaped tactile sensor is effective and high accurate for discriminating the five textures. PMID:24618775

A finger-shaped tactile sensor for fabric surfaces evaluation by 2-dimensional active sliding touch.

PubMed

Hu, Haihua; Han, Yezhen; Song, Aiguo; Chen, Shanguang; Wang, Chunhui; Wang, Zheng

2014-03-11

Sliding tactile perception is a basic function for human beings to determine the mechanical properties of object surfaces and recognize materials. Imitating this process, this paper proposes a novel finger-shaped tactile sensor based on a thin piezoelectric polyvinylidene fluoride (PVDF) film for surface texture measurement. A parallelogram mechanism is designed to ensure that the sensor applies a constant contact force perpendicular to the object surface, and a 2-dimensional movable mechanical structure is utilized to generate the relative motion at a certain speed between the sensor and the object surface. By controlling the 2-dimensional motion of the finger-shaped sensor along the object surface, small height/depth variation of surface texture changes the output charge of PVDF film then surface texture can be measured. In this paper, the finger-shaped tactile sensor is used to evaluate and classify five different kinds of linen. Fast Fourier Transformation (FFT) is utilized to get original attribute data of surface in the frequency domain, and principal component analysis (PCA) is used to compress the attribute data and extract feature information. Finally, low dimensional features are classified by Support Vector Machine (SVM). The experimental results show that this finger-shaped tactile sensor is effective and high accurate for discriminating the five textures.

SU-D-201-05: On the Automatic Recognition of Patient Safety Hazards in a Radiotherapy Setup Using a Novel 3D Camera System and a Deep Learning Framework

DOE Office of Scientific and Technical Information (OSTI.GOV)

Santhanam, A; Min, Y; Beron, P

Purpose: Patient safety hazards such as a wrong patient/site getting treated can lead to catastrophic results. The purpose of this project is to automatically detect potential patient safety hazards during the radiotherapy setup and alert the therapist before the treatment is initiated. Methods: We employed a set of co-located and co-registered 3D cameras placed inside the treatment room. Each camera provided a point-cloud of fraxels (fragment pixels with 3D depth information). Each of the cameras were calibrated using a custom-built calibration target to provide 3D information with less than 2 mm error in the 500 mm neighborhood around the isocenter.more » To identify potential patient safety hazards, the treatment room components and the patient’s body needed to be identified and tracked in real-time. For feature recognition purposes, we used a graph-cut based feature recognition with principal component analysis (PCA) based feature-to-object correlation to segment the objects in real-time. Changes in the object’s position were tracked using the CamShift algorithm. The 3D object information was then stored for each classified object (e.g. gantry, couch). A deep learning framework was then used to analyze all the classified objects in both 2D and 3D and was then used to fine-tune a convolutional network for object recognition. The number of network layers were optimized to identify the tracked objects with >95% accuracy. Results: Our systematic analyses showed that, the system was effectively able to recognize wrong patient setups and wrong patient accessories. The combined usage of 2D camera information (color + depth) enabled a topology-preserving approach to verify patient safety hazards in an automatic manner and even in scenarios where the depth information is partially available. Conclusion: By utilizing the 3D cameras inside the treatment room and a deep learning based image classification, potential patient safety hazards can be effectively avoided.« less

Improving performance of breast cancer risk prediction using a new CAD-based region segmentation scheme

NASA Astrophysics Data System (ADS)

Heidari, Morteza; Zargari Khuzani, Abolfazl; Danala, Gopichandh; Qiu, Yuchen; Zheng, Bin

2018-02-01

Objective of this study is to develop and test a new computer-aided detection (CAD) scheme with improved region of interest (ROI) segmentation combined with an image feature extraction framework to improve performance in predicting short-term breast cancer risk. A dataset involving 570 sets of "prior" negative mammography screening cases was retrospectively assembled. In the next sequential "current" screening, 285 cases were positive and 285 cases remained negative. A CAD scheme was applied to all 570 "prior" negative images to stratify cases into the high and low risk case group of having cancer detected in the "current" screening. First, a new ROI segmentation algorithm was used to automatically remove useless area of mammograms. Second, from the matched bilateral craniocaudal view images, a set of 43 image features related to frequency characteristics of ROIs were initially computed from the discrete cosine transform and spatial domain of the images. Third, a support vector machine model based machine learning classifier was used to optimally classify the selected optimal image features to build a CAD-based risk prediction model. The classifier was trained using a leave-one-case-out based cross-validation method. Applying this improved CAD scheme to the testing dataset, an area under ROC curve, AUC = 0.70+/-0.04, which was significantly higher than using the extracting features directly from the dataset without the improved ROI segmentation step (AUC = 0.63+/-0.04). This study demonstrated that the proposed approach could improve accuracy on predicting short-term breast cancer risk, which may play an important role in helping eventually establish an optimal personalized breast cancer paradigm.

Efficacy Evaluation of Different Wavelet Feature Extraction Methods on Brain MRI Tumor Detection

NASA Astrophysics Data System (ADS)

Nabizadeh, Nooshin; John, Nigel; Kubat, Miroslav

2014-03-01

Automated Magnetic Resonance Imaging brain tumor detection and segmentation is a challenging task. Among different available methods, feature-based methods are very dominant. While many feature extraction techniques have been employed, it is still not quite clear which of feature extraction methods should be preferred. To help improve the situation, we present the results of a study in which we evaluate the efficiency of using different wavelet transform features extraction methods in brain MRI abnormality detection. Applying T1-weighted brain image, Discrete Wavelet Transform (DWT), Discrete Wavelet Packet Transform (DWPT), Dual Tree Complex Wavelet Transform (DTCWT), and Complex Morlet Wavelet Transform (CMWT) methods are applied to construct the feature pool. Three various classifiers as Support Vector Machine, K Nearest Neighborhood, and Sparse Representation-Based Classifier are applied and compared for classifying the selected features. The results show that DTCWT and CMWT features classified with SVM, result in the highest classification accuracy, proving of capability of wavelet transform features to be informative in this application.

A User-Centric Knowledge Creation Model in a Web of Object-Enabled Internet of Things Environment

PubMed Central

Kibria, Muhammad Golam; Fattah, Sheik Mohammad Mostakim; Jeong, Kwanghyeon; Chong, Ilyoung; Jeong, Youn-Kwae

2015-01-01

User-centric service features in a Web of Object-enabled Internet of Things environment can be provided by using a semantic ontology that classifies and integrates objects on the World Wide Web as well as shares and merges context-aware information and accumulated knowledge. The semantic ontology is applied on a Web of Object platform to virtualize the real world physical devices and information to form virtual objects that represent the features and capabilities of devices in the virtual world. Detailed information and functionalities of multiple virtual objects are combined with service rules to form composite virtual objects that offer context-aware knowledge-based services, where context awareness plays an important role in enabling automatic modification of the system to reconfigure the services based on the context. Converting the raw data into meaningful information and connecting the information to form the knowledge and storing and reusing the objects in the knowledge base can both be expressed by semantic ontology. In this paper, a knowledge creation model that synchronizes a service logistic model and a virtual world knowledge model on a Web of Object platform has been proposed. To realize the context-aware knowledge-based service creation and execution, a conceptual semantic ontology model has been developed and a prototype has been implemented for a use case scenario of emergency service. PMID:26393609

A User-Centric Knowledge Creation Model in a Web of Object-Enabled Internet of Things Environment.

PubMed

Kibria, Muhammad Golam; Fattah, Sheik Mohammad Mostakim; Jeong, Kwanghyeon; Chong, Ilyoung; Jeong, Youn-Kwae

2015-09-18

User-centric service features in a Web of Object-enabled Internet of Things environment can be provided by using a semantic ontology that classifies and integrates objects on the World Wide Web as well as shares and merges context-aware information and accumulated knowledge. The semantic ontology is applied on a Web of Object platform to virtualize the real world physical devices and information to form virtual objects that represent the features and capabilities of devices in the virtual world. Detailed information and functionalities of multiple virtual objects are combined with service rules to form composite virtual objects that offer context-aware knowledge-based services, where context awareness plays an important role in enabling automatic modification of the system to reconfigure the services based on the context. Converting the raw data into meaningful information and connecting the information to form the knowledge and storing and reusing the objects in the knowledge base can both be expressed by semantic ontology. In this paper, a knowledge creation model that synchronizes a service logistic model and a virtual world knowledge model on a Web of Object platform has been proposed. To realize the context-aware knowledge-based service creation and execution, a conceptual semantic ontology model has been developed and a prototype has been implemented for a use case scenario of emergency service.

A two-dimensional matrix image based feature extraction method for classification of sEMG: A comparative analysis based on SVM, KNN and RBF-NN.

PubMed

Wen, Tingxi; Zhang, Zhongnan; Qiu, Ming; Zeng, Ming; Luo, Weizhen

2017-01-01

The computer mouse is an important human-computer interaction device. But patients with physical finger disability are unable to operate this device. Surface EMG (sEMG) can be monitored by electrodes on the skin surface and is a reflection of the neuromuscular activities. Therefore, we can control limbs auxiliary equipment by utilizing sEMG classification in order to help the physically disabled patients to operate the mouse. To develop a new a method to extract sEMG generated by finger motion and apply novel features to classify sEMG. A window-based data acquisition method was presented to extract signal samples from sEMG electordes. Afterwards, a two-dimensional matrix image based feature extraction method, which differs from the classical methods based on time domain or frequency domain, was employed to transform signal samples to feature maps used for classification. In the experiments, sEMG data samples produced by the index and middle fingers at the click of a mouse button were separately acquired. Then, characteristics of the samples were analyzed to generate a feature map for each sample. Finally, the machine learning classification algorithms (SVM, KNN, RBF-NN) were employed to classify these feature maps on a GPU. The study demonstrated that all classifiers can identify and classify sEMG samples effectively. In particular, the accuracy of the SVM classifier reached up to 100%. The signal separation method is a convenient, efficient and quick method, which can effectively extract the sEMG samples produced by fingers. In addition, unlike the classical methods, the new method enables to extract features by enlarging sample signals' energy appropriately. The classical machine learning classifiers all performed well by using these features.

A hybrid MLP-CNN classifier for very fine resolution remotely sensed image classification

NASA Astrophysics Data System (ADS)

Zhang, Ce; Pan, Xin; Li, Huapeng; Gardiner, Andy; Sargent, Isabel; Hare, Jonathon; Atkinson, Peter M.

2018-06-01

The contextual-based convolutional neural network (CNN) with deep architecture and pixel-based multilayer perceptron (MLP) with shallow structure are well-recognized neural network algorithms, representing the state-of-the-art deep learning method and the classical non-parametric machine learning approach, respectively. The two algorithms, which have very different behaviours, were integrated in a concise and effective way using a rule-based decision fusion approach for the classification of very fine spatial resolution (VFSR) remotely sensed imagery. The decision fusion rules, designed primarily based on the classification confidence of the CNN, reflect the generally complementary patterns of the individual classifiers. In consequence, the proposed ensemble classifier MLP-CNN harvests the complementary results acquired from the CNN based on deep spatial feature representation and from the MLP based on spectral discrimination. Meanwhile, limitations of the CNN due to the adoption of convolutional filters such as the uncertainty in object boundary partition and loss of useful fine spatial resolution detail were compensated. The effectiveness of the ensemble MLP-CNN classifier was tested in both urban and rural areas using aerial photography together with an additional satellite sensor dataset. The MLP-CNN classifier achieved promising performance, consistently outperforming the pixel-based MLP, spectral and textural-based MLP, and the contextual-based CNN in terms of classification accuracy. This research paves the way to effectively address the complicated problem of VFSR image classification.

Single-trial laser-evoked potentials feature extraction for prediction of pain perception.

PubMed

Huang, Gan; Xiao, Ping; Hu, Li; Hung, Yeung Sam; Zhang, Zhiguo

2013-01-01

Pain is a highly subjective experience, and the availability of an objective assessment of pain perception would be of great importance for both basic and clinical applications. The objective of the present study is to develop a novel approach to extract pain-related features from single-trial laser-evoked potentials (LEPs) for classification of pain perception. The single-trial LEP feature extraction approach combines a spatial filtering using common spatial pattern (CSP) and a multiple linear regression (MLR). The CSP method is effective in separating laser-evoked EEG response from ongoing EEG activity, while MLR is capable of automatically estimating the amplitudes and latencies of N2 and P2 from single-trial LEP waveforms. The extracted single-trial LEP features are used in a Naïve Bayes classifier to classify different levels of pain perceived by the subjects. The experimental results show that the proposed single-trial LEP feature extraction approach can effectively extract pain-related LEP features for achieving high classification accuracy.

Feature and Score Fusion Based Multiple Classifier Selection for Iris Recognition

PubMed Central

Islam, Md. Rabiul

2014-01-01

The aim of this work is to propose a new feature and score fusion based iris recognition approach where voting method on Multiple Classifier Selection technique has been applied. Four Discrete Hidden Markov Model classifiers output, that is, left iris based unimodal system, right iris based unimodal system, left-right iris feature fusion based multimodal system, and left-right iris likelihood ratio score fusion based multimodal system, is combined using voting method to achieve the final recognition result. CASIA-IrisV4 database has been used to measure the performance of the proposed system with various dimensions. Experimental results show the versatility of the proposed system of four different classifiers with various dimensions. Finally, recognition accuracy of the proposed system has been compared with existing N hamming distance score fusion approach proposed by Ma et al., log-likelihood ratio score fusion approach proposed by Schmid et al., and single level feature fusion approach proposed by Hollingsworth et al. PMID:25114676

Feature and score fusion based multiple classifier selection for iris recognition.

PubMed

Islam, Md Rabiul

2014-01-01

The aim of this work is to propose a new feature and score fusion based iris recognition approach where voting method on Multiple Classifier Selection technique has been applied. Four Discrete Hidden Markov Model classifiers output, that is, left iris based unimodal system, right iris based unimodal system, left-right iris feature fusion based multimodal system, and left-right iris likelihood ratio score fusion based multimodal system, is combined using voting method to achieve the final recognition result. CASIA-IrisV4 database has been used to measure the performance of the proposed system with various dimensions. Experimental results show the versatility of the proposed system of four different classifiers with various dimensions. Finally, recognition accuracy of the proposed system has been compared with existing N hamming distance score fusion approach proposed by Ma et al., log-likelihood ratio score fusion approach proposed by Schmid et al., and single level feature fusion approach proposed by Hollingsworth et al.

Automatic morphological classification of galaxy images

PubMed Central

Shamir, Lior

2009-01-01

We describe an image analysis supervised learning algorithm that can automatically classify galaxy images. The algorithm is first trained using a manually classified images of elliptical, spiral, and edge-on galaxies. A large set of image features is extracted from each image, and the most informative features are selected using Fisher scores. Test images can then be classified using a simple Weighted Nearest Neighbor rule such that the Fisher scores are used as the feature weights. Experimental results show that galaxy images from Galaxy Zoo can be classified automatically to spiral, elliptical and edge-on galaxies with accuracy of ~90% compared to classifications carried out by the author. Full compilable source code of the algorithm is available for free download, and its general-purpose nature makes it suitable for other uses that involve automatic image analysis of celestial objects. PMID:20161594

Ensemble Classifier Strategy Based on Transient Feature Fusion in Electronic Nose

NASA Astrophysics Data System (ADS)

Bagheri, Mohammad Ali; Montazer, Gholam Ali

2011-09-01

In this paper, we test the performance of several ensembles of classifiers and each base learner has been trained on different types of extracted features. Experimental results show the potential benefits introduced by the usage of simple ensemble classification systems for the integration of different types of transient features.

New neural-networks-based 3D object recognition system

NASA Astrophysics Data System (ADS)

Abolmaesumi, Purang; Jahed, M.

1997-09-01

Three-dimensional object recognition has always been one of the challenging fields in computer vision. In recent years, Ulman and Basri (1991) have proposed that this task can be done by using a database of 2-D views of the objects. The main problem in their proposed system is that the correspondent points should be known to interpolate the views. On the other hand, their system should have a supervisor to decide which class does the represented view belong to. In this paper, we propose a new momentum-Fourier descriptor that is invariant to scale, translation, and rotation. This descriptor provides the input feature vectors to our proposed system. By using the Dystal network, we show that the objects can be classified with over 95% precision. We have used this system to classify the objects like cube, cone, sphere, torus, and cylinder. Because of the nature of the Dystal network, this system reaches to its stable point by a single representation of the view to the system. This system can also classify the similar views to a single class (e.g., for the cube, the system generated 9 different classes for 50 different input views), which can be used to select an optimum database of training views. The system is also very flexible to the noise and deformed views.

Improving lung cancer prognosis assessment by incorporating synthetic minority oversampling technique and score fusion method

DOE Office of Scientific and Technical Information (OSTI.GOV)

Yan, Shiju; Qian, Wei; Guan, Yubao

2016-06-15

Purpose: This study aims to investigate the potential to improve lung cancer recurrence risk prediction performance for stage I NSCLS patients by integrating oversampling, feature selection, and score fusion techniques and develop an optimal prediction model. Methods: A dataset involving 94 early stage lung cancer patients was retrospectively assembled, which includes CT images, nine clinical and biological (CB) markers, and outcome of 3-yr disease-free survival (DFS) after surgery. Among the 94 patients, 74 remained DFS and 20 had cancer recurrence. Applying a computer-aided detection scheme, tumors were segmented from the CT images and 35 quantitative image (QI) features were initiallymore » computed. Two normalized Gaussian radial basis function network (RBFN) based classifiers were built based on QI features and CB markers separately. To improve prediction performance, the authors applied a synthetic minority oversampling technique (SMOTE) and a BestFirst based feature selection method to optimize the classifiers and also tested fusion methods to combine QI and CB based prediction results. Results: Using a leave-one-case-out cross-validation (K-fold cross-validation) method, the computed areas under a receiver operating characteristic curve (AUCs) were 0.716 ± 0.071 and 0.642 ± 0.061, when using the QI and CB based classifiers, respectively. By fusion of the scores generated by the two classifiers, AUC significantly increased to 0.859 ± 0.052 (p < 0.05) with an overall prediction accuracy of 89.4%. Conclusions: This study demonstrated the feasibility of improving prediction performance by integrating SMOTE, feature selection, and score fusion techniques. Combining QI features and CB markers and performing SMOTE prior to feature selection in classifier training enabled RBFN based classifier to yield improved prediction accuracy.« less

Bayesian network classifiers for categorizing cortical GABAergic interneurons.

PubMed

Mihaljević, Bojan; Benavides-Piccione, Ruth; Bielza, Concha; DeFelipe, Javier; Larrañaga, Pedro

2015-04-01

An accepted classification of GABAergic interneurons of the cerebral cortex is a major goal in neuroscience. A recently proposed taxonomy based on patterns of axonal arborization promises to be a pragmatic method for achieving this goal. It involves characterizing interneurons according to five axonal arborization features, called F1-F5, and classifying them into a set of predefined types, most of which are established in the literature. Unfortunately, there is little consensus among expert neuroscientists regarding the morphological definitions of some of the proposed types. While supervised classifiers were able to categorize the interneurons in accordance with experts' assignments, their accuracy was limited because they were trained with disputed labels. Thus, here we automatically classify interneuron subsets with different label reliability thresholds (i.e., such that every cell's label is backed by at least a certain (threshold) number of experts). We quantify the cells with parameters of axonal and dendritic morphologies and, in order to predict the type, also with axonal features F1-F4 provided by the experts. Using Bayesian network classifiers, we accurately characterize and classify the interneurons and identify useful predictor variables. In particular, we discriminate among reliable examples of common basket, horse-tail, large basket, and Martinotti cells with up to 89.52% accuracy, and single out the number of branches at 180 μm from the soma, the convex hull 2D area, and the axonal features F1-F4 as especially useful predictors for distinguishing among these types. These results open up new possibilities for an objective and pragmatic classification of interneurons.

Classification and pose estimation of objects using nonlinear features

NASA Astrophysics Data System (ADS)

Talukder, Ashit; Casasent, David P.

1998-03-01

A new nonlinear feature extraction method called the maximum representation and discrimination feature (MRDF) method is presented for extraction of features from input image data. It implements transformations similar to the Sigma-Pi neural network. However, the weights of the MRDF are obtained in closed form, and offer advantages compared to nonlinear neural network implementations. The features extracted are useful for both object discrimination (classification) and object representation (pose estimation). We show its use in estimating the class and pose of images of real objects and rendered solid CAD models of machine parts from single views using a feature-space trajectory (FST) neural network classifier. We show more accurate classification and pose estimation results than are achieved by standard principal component analysis (PCA) and Fukunaga-Koontz (FK) feature extraction methods.

Hybrid ANN optimized artificial fish swarm algorithm based classifier for classification of suspicious lesions in breast DCE-MRI

NASA Astrophysics Data System (ADS)

Janaki Sathya, D.; Geetha, K.

2017-12-01

Automatic mass or lesion classification systems are developed to aid in distinguishing between malignant and benign lesions present in the breast DCE-MR images, the systems need to improve both the sensitivity and specificity of DCE-MR image interpretation in order to be successful for clinical use. A new classifier (a set of features together with a classification method) based on artificial neural networks trained using artificial fish swarm optimization (AFSO) algorithm is proposed in this paper. The basic idea behind the proposed classifier is to use AFSO algorithm for searching the best combination of synaptic weights for the neural network. An optimal set of features based on the statistical textural features is presented. The investigational outcomes of the proposed suspicious lesion classifier algorithm therefore confirm that the resulting classifier performs better than other such classifiers reported in the literature. Therefore this classifier demonstrates that the improvement in both the sensitivity and specificity are possible through automated image analysis.

Automatic Identification of Messages Related to Adverse Drug Reactions from Online User Reviews using Feature-based Classification.

PubMed

Liu, Jingfang; Zhang, Pengzhu; Lu, Yingjie

2014-11-01

User-generated medical messages on Internet contain extensive information related to adverse drug reactions (ADRs) and are known as valuable resources for post-marketing drug surveillance. The aim of this study was to find an effective method to identify messages related to ADRs automatically from online user reviews. We conducted experiments on online user reviews using different feature set and different classification technique. Firstly, the messages from three communities, allergy community, schizophrenia community and pain management community, were collected, the 3000 messages were annotated. Secondly, the N-gram-based features set and medical domain-specific features set were generated. Thirdly, three classification techniques, SVM, C4.5 and Naïve Bayes, were used to perform classification tasks separately. Finally, we evaluated the performance of different method using different feature set and different classification technique by comparing the metrics including accuracy and F-measure. In terms of accuracy, the accuracy of SVM classifier was higher than 0.8, the accuracy of C4.5 classifier or Naïve Bayes classifier was lower than 0.8; meanwhile, the combination feature sets including n-gram-based feature set and domain-specific feature set consistently outperformed single feature set. In terms of F-measure, the highest F-measure is 0.895 which was achieved by using combination feature sets and a SVM classifier. In all, we can get the best classification performance by using combination feature sets and SVM classifier. By using combination feature sets and SVM classifier, we can get an effective method to identify messages related to ADRs automatically from online user reviews.

Snoring classified: The Munich-Passau Snore Sound Corpus.

PubMed

Janott, Christoph; Schmitt, Maximilian; Zhang, Yue; Qian, Kun; Pandit, Vedhas; Zhang, Zixing; Heiser, Clemens; Hohenhorst, Winfried; Herzog, Michael; Hemmert, Werner; Schuller, Björn

2018-03-01

Snoring can be excited in different locations within the upper airways during sleep. It was hypothesised that the excitation locations are correlated with distinct acoustic characteristics of the snoring noise. To verify this hypothesis, a database of snore sounds is developed, labelled with the location of sound excitation. Video and audio recordings taken during drug induced sleep endoscopy (DISE) examinations from three medical centres have been semi-automatically screened for snore events, which subsequently have been classified by ENT experts into four classes based on the VOTE classification. The resulting dataset containing 828 snore events from 219 subjects has been split into Train, Development, and Test sets. An SVM classifier has been trained using low level descriptors (LLDs) related to energy, spectral features, mel frequency cepstral coefficients (MFCC), formants, voicing, harmonic-to-noise ratio (HNR), spectral harmonicity, pitch, and microprosodic features. An unweighted average recall (UAR) of 55.8% could be achieved using the full set of LLDs including formants. Best performing subset is the MFCC-related set of LLDs. A strong difference in performance could be observed between the permutations of train, development, and test partition, which may be caused by the relatively low number of subjects included in the smaller classes of the strongly unbalanced data set. A database of snoring sounds is presented which are classified according to their sound excitation location based on objective criteria and verifiable video material. With the database, it could be demonstrated that machine classifiers can distinguish different excitation location of snoring sounds in the upper airway based on acoustic parameters. Copyright © 2018 Elsevier Ltd. All rights reserved.

Systematic evaluation of deep learning based detection frameworks for aerial imagery

NASA Astrophysics Data System (ADS)

Sommer, Lars; Steinmann, Lucas; Schumann, Arne; Beyerer, Jürgen

2018-04-01

Object detection in aerial imagery is crucial for many applications in the civil and military domain. In recent years, deep learning based object detection frameworks significantly outperformed conventional approaches based on hand-crafted features on several datasets. However, these detection frameworks are generally designed and optimized for common benchmark datasets, which considerably differ from aerial imagery especially in object sizes. As already demonstrated for Faster R-CNN, several adaptations are necessary to account for these differences. In this work, we adapt several state-of-the-art detection frameworks including Faster R-CNN, R-FCN, and Single Shot MultiBox Detector (SSD) to aerial imagery. We discuss adaptations that mainly improve the detection accuracy of all frameworks in detail. As the output of deeper convolutional layers comprise more semantic information, these layers are generally used in detection frameworks as feature map to locate and classify objects. However, the resolution of these feature maps is insufficient for handling small object instances, which results in an inaccurate localization or incorrect classification of small objects. Furthermore, state-of-the-art detection frameworks perform bounding box regression to predict the exact object location. Therefore, so called anchor or default boxes are used as reference. We demonstrate how an appropriate choice of anchor box sizes can considerably improve detection performance. Furthermore, we evaluate the impact of the performed adaptations on two publicly available datasets to account for various ground sampling distances or differing backgrounds. The presented adaptations can be used as guideline for further datasets or detection frameworks.

Artificial intelligence (AI) systems for interpreting complex medical datasets.

PubMed

Altman, R B

2017-05-01

Advances in machine intelligence have created powerful capabilities in algorithms that find hidden patterns in data, classify objects based on their measured characteristics, and associate similar patients/diseases/drugs based on common features. However, artificial intelligence (AI) applications in medical data have several technical challenges: complex and heterogeneous datasets, noisy medical datasets, and explaining their output to users. There are also social challenges related to intellectual property, data provenance, regulatory issues, economics, and liability. © 2017 ASCPT.

Single-Pol Synthetic Aperture Radar Terrain Classification using Multiclass Confidence for One-Class Classifiers

DOE Office of Scientific and Technical Information (OSTI.GOV)

Koch, Mark William; Steinbach, Ryan Matthew; Moya, Mary M

2015-10-01

Except in the most extreme conditions, Synthetic aperture radar (SAR) is a remote sensing technology that can operate day or night. A SAR can provide surveillance over a long time period by making multiple passes over a wide area. For object-based intelligence it is convenient to segment and classify the SAR images into objects that identify various terrains and man-made structures that we call “static features.” In this paper we introduce a novel SAR image product that captures how different regions decorrelate at different rates. Using superpixels and their first two moments we develop a series of one-class classification algorithmsmore » using a goodness-of-fit metric. P-value fusion is used to combine the results from different classes. We also show how to combine multiple one-class classifiers to get a confidence about a classification. This can be used by downstream algorithms such as a conditional random field to enforce spatial constraints.« less

Classification of Informal Settlements Through the Integration of 2d and 3d Features Extracted from Uav Data

NASA Astrophysics Data System (ADS)

Gevaert, C. M.; Persello, C.; Sliuzas, R.; Vosselman, G.

2016-06-01

Unmanned Aerial Vehicles (UAVs) are capable of providing very high resolution and up-to-date information to support informal settlement upgrading projects. In order to provide accurate basemaps, urban scene understanding through the identification and classification of buildings and terrain is imperative. However, common characteristics of informal settlements such as small, irregular buildings with heterogeneous roof material and large presence of clutter challenge state-of-the-art algorithms. Especially the dense buildings and steeply sloped terrain cause difficulties in identifying elevated objects. This work investigates how 2D radiometric and textural features, 2.5D topographic features, and 3D geometric features obtained from UAV imagery can be integrated to obtain a high classification accuracy in challenging classification problems for the analysis of informal settlements. It compares the utility of pixel-based and segment-based features obtained from an orthomosaic and DSM with point-based and segment-based features extracted from the point cloud to classify an unplanned settlement in Kigali, Rwanda. Findings show that the integration of 2D and 3D features leads to higher classification accuracies.

Adaptive learning compressive tracking based on Markov location prediction

NASA Astrophysics Data System (ADS)

Zhou, Xingyu; Fu, Dongmei; Yang, Tao; Shi, Yanan

2017-03-01

Object tracking is an interdisciplinary research topic in image processing, pattern recognition, and computer vision which has theoretical and practical application value in video surveillance, virtual reality, and automatic navigation. Compressive tracking (CT) has many advantages, such as efficiency and accuracy. However, when there are object occlusion, abrupt motion and blur, similar objects, and scale changing, the CT has the problem of tracking drift. We propose the Markov object location prediction to get the initial position of the object. Then CT is used to locate the object accurately, and the classifier parameter adaptive updating strategy is given based on the confidence map. At the same time according to the object location, extract the scale features, which is able to deal with object scale variations effectively. Experimental results show that the proposed algorithm has better tracking accuracy and robustness than current advanced algorithms and achieves real-time performance.

User-customized brain computer interfaces using Bayesian optimization

NASA Astrophysics Data System (ADS)

Bashashati, Hossein; Ward, Rabab K.; Bashashati, Ali

2016-04-01

Objective. The brain characteristics of different people are not the same. Brain computer interfaces (BCIs) should thus be customized for each individual person. In motor-imagery based synchronous BCIs, a number of parameters (referred to as hyper-parameters) including the EEG frequency bands, the channels and the time intervals from which the features are extracted should be pre-determined based on each subject’s brain characteristics. Approach. To determine the hyper-parameter values, previous work has relied on manual or semi-automatic methods that are not applicable to high-dimensional search spaces. In this paper, we propose a fully automatic, scalable and computationally inexpensive algorithm that uses Bayesian optimization to tune these hyper-parameters. We then build different classifiers trained on the sets of hyper-parameter values proposed by the Bayesian optimization. A final classifier aggregates the results of the different classifiers. Main Results. We have applied our method to 21 subjects from three BCI competition datasets. We have conducted rigorous statistical tests, and have shown the positive impact of hyper-parameter optimization in improving the accuracy of BCIs. Furthermore, We have compared our results to those reported in the literature. Significance. Unlike the best reported results in the literature, which are based on more sophisticated feature extraction and classification methods, and rely on prestudies to determine the hyper-parameter values, our method has the advantage of being fully automated, uses less sophisticated feature extraction and classification methods, and yields similar or superior results compared to the best performing designs in the literature.

Feature selection for wearable smartphone-based human activity recognition with able bodied, elderly, and stroke patients.

PubMed

Capela, Nicole A; Lemaire, Edward D; Baddour, Natalie

2015-01-01

Human activity recognition (HAR), using wearable sensors, is a growing area with the potential to provide valuable information on patient mobility to rehabilitation specialists. Smartphones with accelerometer and gyroscope sensors are a convenient, minimally invasive, and low cost approach for mobility monitoring. HAR systems typically pre-process raw signals, segment the signals, and then extract features to be used in a classifier. Feature selection is a crucial step in the process to reduce potentially large data dimensionality and provide viable parameters to enable activity classification. Most HAR systems are customized to an individual research group, including a unique data set, classes, algorithms, and signal features. These data sets are obtained predominantly from able-bodied participants. In this paper, smartphone accelerometer and gyroscope sensor data were collected from populations that can benefit from human activity recognition: able-bodied, elderly, and stroke patients. Data from a consecutive sequence of 41 mobility tasks (18 different tasks) were collected for a total of 44 participants. Seventy-six signal features were calculated and subsets of these features were selected using three filter-based, classifier-independent, feature selection methods (Relief-F, Correlation-based Feature Selection, Fast Correlation Based Filter). The feature subsets were then evaluated using three generic classifiers (Naïve Bayes, Support Vector Machine, j48 Decision Tree). Common features were identified for all three populations, although the stroke population subset had some differences from both able-bodied and elderly sets. Evaluation with the three classifiers showed that the feature subsets produced similar or better accuracies than classification with the entire feature set. Therefore, since these feature subsets are classifier-independent, they should be useful for developing and improving HAR systems across and within populations.

Feature Selection for Wearable Smartphone-Based Human Activity Recognition with Able bodied, Elderly, and Stroke Patients

PubMed Central

2015-01-01

Human activity recognition (HAR), using wearable sensors, is a growing area with the potential to provide valuable information on patient mobility to rehabilitation specialists. Smartphones with accelerometer and gyroscope sensors are a convenient, minimally invasive, and low cost approach for mobility monitoring. HAR systems typically pre-process raw signals, segment the signals, and then extract features to be used in a classifier. Feature selection is a crucial step in the process to reduce potentially large data dimensionality and provide viable parameters to enable activity classification. Most HAR systems are customized to an individual research group, including a unique data set, classes, algorithms, and signal features. These data sets are obtained predominantly from able-bodied participants. In this paper, smartphone accelerometer and gyroscope sensor data were collected from populations that can benefit from human activity recognition: able-bodied, elderly, and stroke patients. Data from a consecutive sequence of 41 mobility tasks (18 different tasks) were collected for a total of 44 participants. Seventy-six signal features were calculated and subsets of these features were selected using three filter-based, classifier-independent, feature selection methods (Relief-F, Correlation-based Feature Selection, Fast Correlation Based Filter). The feature subsets were then evaluated using three generic classifiers (Naïve Bayes, Support Vector Machine, j48 Decision Tree). Common features were identified for all three populations, although the stroke population subset had some differences from both able-bodied and elderly sets. Evaluation with the three classifiers showed that the feature subsets produced similar or better accuracies than classification with the entire feature set. Therefore, since these feature subsets are classifier-independent, they should be useful for developing and improving HAR systems across and within populations. PMID:25885272

Chaotic particle swarm optimization with mutation for classification.

PubMed

Assarzadeh, Zahra; Naghsh-Nilchi, Ahmad Reza

2015-01-01

In this paper, a chaotic particle swarm optimization with mutation-based classifier particle swarm optimization is proposed to classify patterns of different classes in the feature space. The introduced mutation operators and chaotic sequences allows us to overcome the problem of early convergence into a local minima associated with particle swarm optimization algorithms. That is, the mutation operator sharpens the convergence and it tunes the best possible solution. Furthermore, to remove the irrelevant data and reduce the dimensionality of medical datasets, a feature selection approach using binary version of the proposed particle swarm optimization is introduced. In order to demonstrate the effectiveness of our proposed classifier, mutation-based classifier particle swarm optimization, it is checked out with three sets of data classifications namely, Wisconsin diagnostic breast cancer, Wisconsin breast cancer and heart-statlog, with different feature vector dimensions. The proposed algorithm is compared with different classifier algorithms including k-nearest neighbor, as a conventional classifier, particle swarm-classifier, genetic algorithm, and Imperialist competitive algorithm-classifier, as more sophisticated ones. The performance of each classifier was evaluated by calculating the accuracy, sensitivity, specificity and Matthews's correlation coefficient. The experimental results show that the mutation-based classifier particle swarm optimization unequivocally performs better than all the compared algorithms.

Classification of breast abnormalities using artificial neural network

NASA Astrophysics Data System (ADS)

Zaman, Nur Atiqah Kamarul; Rahman, Wan Eny Zarina Wan Abdul; Jumaat, Abdul Kadir; Yasiran, Siti Salmah

2015-05-01

Classification is the process of recognition, differentiation and categorizing objects into groups. Breast abnormalities are calcifications which are tumor markers that indicate the presence of cancer in the breast. The aims of this research are to classify the types of breast abnormalities using artificial neural network (ANN) classifier and to evaluate the accuracy performance using receiver operating characteristics (ROC) curve. The methods used in this research are ANN for breast abnormalities classifications and Canny edge detector as a feature extraction method. Previously the ANN classifier provides only the number of benign and malignant cases without providing information for specific cases. However in this research, the type of abnormality for each image can be obtained. The existing MIAS MiniMammographic database classified the mammogram images into three features only namely characteristic of background tissues, class of abnormality and radius of abnormality. However, in this research three other features are added-in. These three features are number of spots, area and shape of abnormalities. Lastly the performance of the ANN classifier is evaluated using ROC curve. It is found that ANN has an accuracy of 97.9% which is considered acceptable.

Detection of acute lymphocyte leukemia using k-nearest neighbor algorithm based on shape and histogram features

NASA Astrophysics Data System (ADS)

Purwanti, Endah; Calista, Evelyn

2017-05-01

Leukemia is a type of cancer which is caused by malignant neoplasms in leukocyte cells. Leukemia disease which can cause death quickly enough for the sufferer is a type of acute lymphocyte leukemia (ALL). In this study, we propose automatic detection of lymphocyte leukemia through classification of lymphocyte cell images obtained from peripheral blood smear single cell. There are two main objectives in this study. The first is to extract featuring cells. The second objective is to classify the lymphocyte cells into two classes, namely normal and abnormal lymphocytes. In conducting this study, we use combination of shape feature and histogram feature, and the classification algorithm is k-nearest Neighbour with k variation is 1, 3, 5, 7, 9, 11, 13, and 15. The best level of accuracy, sensitivity, and specificity in this study are 90%, 90%, and 90%, and they were obtained from combined features of area-perimeter-mean-standard deviation with k=7.

Sensing Urban Land-Use Patterns by Integrating Google Tensorflow and Scene-Classification Models

NASA Astrophysics Data System (ADS)

Yao, Y.; Liang, H.; Li, X.; Zhang, J.; He, J.

2017-09-01

With the rapid progress of China's urbanization, research on the automatic detection of land-use patterns in Chinese cities is of substantial importance. Deep learning is an effective method to extract image features. To take advantage of the deep-learning method in detecting urban land-use patterns, we applied a transfer-learning-based remote-sensing image approach to extract and classify features. Using the Google Tensorflow framework, a powerful convolution neural network (CNN) library was created. First, the transferred model was previously trained on ImageNet, one of the largest object-image data sets, to fully develop the model's ability to generate feature vectors of standard remote-sensing land-cover data sets (UC Merced and WHU-SIRI). Then, a random-forest-based classifier was constructed and trained on these generated vectors to classify the actual urban land-use pattern on the scale of traffic analysis zones (TAZs). To avoid the multi-scale effect of remote-sensing imagery, a large random patch (LRP) method was used. The proposed method could efficiently obtain acceptable accuracy (OA = 0.794, Kappa = 0.737) for the study area. In addition, the results show that the proposed method can effectively overcome the multi-scale effect that occurs in urban land-use classification at the irregular land-parcel level. The proposed method can help planners monitor dynamic urban land use and evaluate the impact of urban-planning schemes.

Multiclass cancer classification using a feature subset-based ensemble from microRNA expression profiles.

PubMed

Piao, Yongjun; Piao, Minghao; Ryu, Keun Ho

2017-01-01

Cancer classification has been a crucial topic of research in cancer treatment. In the last decade, messenger RNA (mRNA) expression profiles have been widely used to classify different types of cancers. With the discovery of a new class of small non-coding RNAs; known as microRNAs (miRNAs), various studies have shown that the expression patterns of miRNA can also accurately classify human cancers. Therefore, there is a great demand for the development of machine learning approaches to accurately classify various types of cancers using miRNA expression data. In this article, we propose a feature subset-based ensemble method in which each model is learned from a different projection of the original feature space to classify multiple cancers. In our method, the feature relevance and redundancy are considered to generate multiple feature subsets, the base classifiers are learned from each independent miRNA subset, and the average posterior probability is used to combine the base classifiers. To test the performance of our method, we used bead-based and sequence-based miRNA expression datasets and conducted 10-fold and leave-one-out cross validations. The experimental results show that the proposed method yields good results and has higher prediction accuracy than popular ensemble methods. The Java program and source code of the proposed method and the datasets in the experiments are freely available at https://sourceforge.net/projects/mirna-ensemble/. Copyright © 2016 Elsevier Ltd. All rights reserved.

A fuzzy automated object classification by infrared laser camera

NASA Astrophysics Data System (ADS)

Kanazawa, Seigo; Taniguchi, Kazuhiko; Asari, Kazunari; Kuramoto, Kei; Kobashi, Syoji; Hata, Yutaka

2011-06-01

Home security in night is very important, and the system that watches a person's movements is useful in the security. This paper describes a classification system of adult, child and the other object from distance distribution measured by an infrared laser camera. This camera radiates near infrared waves and receives reflected ones. Then, it converts the time of flight into distance distribution. Our method consists of 4 steps. First, we do background subtraction and noise rejection in the distance distribution. Second, we do fuzzy clustering in the distance distribution, and form several clusters. Third, we extract features such as the height, thickness, aspect ratio, area ratio of the cluster. Then, we make fuzzy if-then rules from knowledge of adult, child and the other object so as to classify the cluster to one of adult, child and the other object. Here, we made the fuzzy membership function with respect to each features. Finally, we classify the clusters to one with the highest fuzzy degree among adult, child and the other object. In our experiment, we set up the camera in room and tested three cases. The method successfully classified them in real time processing.

An Automatic Diagnosis Method of Facial Acne Vulgaris Based on Convolutional Neural Network.

PubMed

Shen, Xiaolei; Zhang, Jiachi; Yan, Chenjun; Zhou, Hong

2018-04-11

In this paper, we present a new automatic diagnosis method for facial acne vulgaris which is based on convolutional neural networks (CNNs). To overcome the shortcomings of previous methods which were the inability to classify enough types of acne vulgaris. The core of our method is to extract features of images based on CNNs and achieve classification by classifier. A binary-classifier of skin-and-non-skin is used to detect skin area and a seven-classifier is used to achieve the classification task of facial acne vulgaris and healthy skin. In the experiments, we compare the effectiveness of our CNN and the VGG16 neural network which is pre-trained on the ImageNet data set. We use a ROC curve to evaluate the performance of binary-classifier and use a normalized confusion matrix to evaluate the performance of seven-classifier. The results of our experiments show that the pre-trained VGG16 neural network is effective in extracting features from facial acne vulgaris images. And the features are very useful for the follow-up classifiers. Finally, we try applying the classifiers both based on the pre-trained VGG16 neural network to assist doctors in facial acne vulgaris diagnosis.

Bias and Stability of Single Variable Classifiers for Feature Ranking and Selection

PubMed Central

Fakhraei, Shobeir; Soltanian-Zadeh, Hamid; Fotouhi, Farshad

2014-01-01

Feature rankings are often used for supervised dimension reduction especially when discriminating power of each feature is of interest, dimensionality of dataset is extremely high, or computational power is limited to perform more complicated methods. In practice, it is recommended to start dimension reduction via simple methods such as feature rankings before applying more complex approaches. Single Variable Classifier (SVC) ranking is a feature ranking based on the predictive performance of a classifier built using only a single feature. While benefiting from capabilities of classifiers, this ranking method is not as computationally intensive as wrappers. In this paper, we report the results of an extensive study on the bias and stability of such feature ranking method. We study whether the classifiers influence the SVC rankings or the discriminative power of features themselves has a dominant impact on the final rankings. We show the common intuition of using the same classifier for feature ranking and final classification does not always result in the best prediction performance. We then study if heterogeneous classifiers ensemble approaches provide more unbiased rankings and if they improve final classification performance. Furthermore, we calculate an empirical prediction performance loss for using the same classifier in SVC feature ranking and final classification from the optimal choices. PMID:25177107

Bias and Stability of Single Variable Classifiers for Feature Ranking and Selection.

PubMed

Fakhraei, Shobeir; Soltanian-Zadeh, Hamid; Fotouhi, Farshad

2014-11-01

Feature rankings are often used for supervised dimension reduction especially when discriminating power of each feature is of interest, dimensionality of dataset is extremely high, or computational power is limited to perform more complicated methods. In practice, it is recommended to start dimension reduction via simple methods such as feature rankings before applying more complex approaches. Single Variable Classifier (SVC) ranking is a feature ranking based on the predictive performance of a classifier built using only a single feature. While benefiting from capabilities of classifiers, this ranking method is not as computationally intensive as wrappers. In this paper, we report the results of an extensive study on the bias and stability of such feature ranking method. We study whether the classifiers influence the SVC rankings or the discriminative power of features themselves has a dominant impact on the final rankings. We show the common intuition of using the same classifier for feature ranking and final classification does not always result in the best prediction performance. We then study if heterogeneous classifiers ensemble approaches provide more unbiased rankings and if they improve final classification performance. Furthermore, we calculate an empirical prediction performance loss for using the same classifier in SVC feature ranking and final classification from the optimal choices.

A Pareto-based Ensemble with Feature and Instance Selection for Learning from Multi-Class Imbalanced Datasets.

PubMed

Fernández, Alberto; Carmona, Cristobal José; José Del Jesus, María; Herrera, Francisco

2017-09-01

Imbalanced classification is related to those problems that have an uneven distribution among classes. In addition to the former, when instances are located into the overlapped areas, the correct modeling of the problem becomes harder. Current solutions for both issues are often focused on the binary case study, as multi-class datasets require an additional effort to be addressed. In this research, we overcome these problems by carrying out a combination between feature and instance selections. Feature selection will allow simplifying the overlapping areas easing the generation of rules to distinguish among the classes. Selection of instances from all classes will address the imbalance itself by finding the most appropriate class distribution for the learning task, as well as possibly removing noise and difficult borderline examples. For the sake of obtaining an optimal joint set of features and instances, we embedded the searching for both parameters in a Multi-Objective Evolutionary Algorithm, using the C4.5 decision tree as baseline classifier in this wrapper approach. The multi-objective scheme allows taking a double advantage: the search space becomes broader, and we may provide a set of different solutions in order to build an ensemble of classifiers. This proposal has been contrasted versus several state-of-the-art solutions on imbalanced classification showing excellent results in both binary and multi-class problems.

Multi-objects recognition for distributed intelligent sensor networks

NASA Astrophysics Data System (ADS)

He, Haibo; Chen, Sheng; Cao, Yuan; Desai, Sachi; Hohil, Myron E.

2008-04-01

This paper proposes an innovative approach for multi-objects recognition for homeland security and defense based intelligent sensor networks. Unlike the conventional way of information analysis, data mining in such networks is typically characterized with high information ambiguity/uncertainty, data redundancy, high dimensionality and real-time constrains. Furthermore, since a typical military based network normally includes multiple mobile sensor platforms, ground forces, fortified tanks, combat flights, and other resources, it is critical to develop intelligent data mining approaches to fuse different information resources to understand dynamic environments, to support decision making processes, and finally to achieve the goals. This paper aims to address these issues with a focus on multi-objects recognition. Instead of classifying a single object as in the traditional image classification problems, the proposed method can automatically learn multiple objectives simultaneously. Image segmentation techniques are used to identify the interesting regions in the field, which correspond to multiple objects such as soldiers or tanks. Since different objects will come with different feature sizes, we propose a feature scaling method to represent each object in the same number of dimensions. This is achieved by linear/nonlinear scaling and sampling techniques. Finally, support vector machine (SVM) based learning algorithms are developed to learn and build the associations for different objects, and such knowledge will be adaptively accumulated for objects recognition in the testing stage. We test the effectiveness of proposed method in different simulated military environments.

Benefits of Red-Edge Spectral Band and Texture Features for the Object-based Classification using RapidEye sSatellite Image data

NASA Astrophysics Data System (ADS)

Kim, H. O.; Yeom, J. M.

2014-12-01

Space-based remote sensing in agriculture is particularly relevant to issues such as global climate change, food security, and precision agriculture. Recent satellite missions have opened up new perspectives by offering high spatial resolution, various spectral properties, and fast revisit rates to the same regions. Here, we examine the utility of broadband red-edge spectral information in multispectral satellite image data for classifying paddy rice crops in South Korea. Additionally, we examine how object-based spectral features affect the classification of paddy rice growth stages. For the analysis, two seasons of RapidEye satellite image data were used. The results showed that the broadband red-edge information slightly improved the classification accuracy of the crop condition in heterogeneous paddy rice crop environments, particularly when single-season image data were used. This positive effect appeared to be offset by the multi-temporal image data. Additional texture information brought only a minor improvement or a slight decline, although it is well known to be advantageous for object-based classification in general. We conclude that broadband red-edge information derived from conventional multispectral satellite data has the potential to improve space-based crop monitoring. Because the positive or negative effects of texture features for object-based crop classification could barely be interpreted, the relationships between the textual properties and paddy rice crop parameters at the field scale should be further examined in depth.

Fusion of pixel and object-based features for weed mapping using unmanned aerial vehicle imagery

NASA Astrophysics Data System (ADS)

Gao, Junfeng; Liao, Wenzhi; Nuyttens, David; Lootens, Peter; Vangeyte, Jürgen; Pižurica, Aleksandra; He, Yong; Pieters, Jan G.

2018-05-01

The developments in the use of unmanned aerial vehicles (UAVs) and advanced imaging sensors provide new opportunities for ultra-high resolution (e.g., less than a 10 cm ground sampling distance (GSD)) crop field monitoring and mapping in precision agriculture applications. In this study, we developed a strategy for inter- and intra-row weed detection in early season maize fields from aerial visual imagery. More specifically, the Hough transform algorithm (HT) was applied to the orthomosaicked images for inter-row weed detection. A semi-automatic Object-Based Image Analysis (OBIA) procedure was developed with Random Forests (RF) combined with feature selection techniques to classify soil, weeds and maize. Furthermore, the two binary weed masks generated from HT and OBIA were fused for accurate binary weed image. The developed RF classifier was evaluated by 5-fold cross validation, and it obtained an overall accuracy of 0.945, and Kappa value of 0.912. Finally, the relationship of detected weeds and their ground truth densities was quantified by a fitted linear model with a coefficient of determination of 0.895 and a root mean square error of 0.026. Besides, the importance of input features was evaluated, and it was found that the ratio of vegetation length and width was the most significant feature for the classification model. Overall, our approach can yield a satisfactory weed map, and we expect that the obtained accurate and timely weed map from UAV imagery will be applicable to realize site-specific weed management (SSWM) in early season crop fields for reducing spraying non-selective herbicides and costs.

Image object recognition based on the Zernike moment and neural networks

NASA Astrophysics Data System (ADS)

Wan, Jianwei; Wang, Ling; Huang, Fukan; Zhou, Liangzhu

1998-03-01

This paper first give a comprehensive discussion about the concept of artificial neural network its research methods and the relations with information processing. On the basis of such a discussion, we expound the mathematical similarity of artificial neural network and information processing. Then, the paper presents a new method of image recognition based on invariant features and neural network by using image Zernike transform. The method not only has the invariant properties for rotation, shift and scale of image object, but also has good fault tolerance and robustness. Meanwhile, it is also compared with statistical classifier and invariant moments recognition method.

Webcam classification using simple features

NASA Astrophysics Data System (ADS)

Pramoun, Thitiporn; Choe, Jeehyun; Li, He; Chen, Qingshuang; Amornraksa, Thumrongrat; Lu, Yung-Hsiang; Delp, Edward J.

2015-03-01

Thousands of sensors are connected to the Internet and many of these sensors are cameras. The "Internet of Things" will contain many "things" that are image sensors. This vast network of distributed cameras (i.e. web cams) will continue to exponentially grow. In this paper we examine simple methods to classify an image from a web cam as "indoor/outdoor" and having "people/no people" based on simple features. We use four types of image features to classify an image as indoor/outdoor: color, edge, line, and text. To classify an image as having people/no people we use HOG and texture features. The features are weighted based on their significance and combined. A support vector machine is used for classification. Our system with feature weighting and feature combination yields 95.5% accuracy.

Mapping of High Value Crops Through AN Object-Based Svm Model Using LIDAR Data and Orthophoto in Agusan del Norte Philippines

NASA Astrophysics Data System (ADS)

Candare, Rudolph Joshua; Japitana, Michelle; Cubillas, James Earl; Ramirez, Cherry Bryan

2016-06-01

This research describes the methods involved in the mapping of different high value crops in Agusan del Norte Philippines using LiDAR. This project is part of the Phil-LiDAR 2 Program which aims to conduct a nationwide resource assessment using LiDAR. Because of the high resolution data involved, the methodology described here utilizes object-based image analysis and the use of optimal features from LiDAR data and Orthophoto. Object-based classification was primarily done by developing rule-sets in eCognition. Several features from the LiDAR data and Orthophotos were used in the development of rule-sets for classification. Generally, classes of objects can't be separated by simple thresholds from different features making it difficult to develop a rule-set. To resolve this problem, the image-objects were subjected to Support Vector Machine learning. SVMs have gained popularity because of their ability to generalize well given a limited number of training samples. However, SVMs also suffer from parameter assignment issues that can significantly affect the classification results. More specifically, the regularization parameter C in linear SVM has to be optimized through cross validation to increase the overall accuracy. After performing the segmentation in eCognition, the optimization procedure as well as the extraction of the equations of the hyper-planes was done in Matlab. The learned hyper-planes separating one class from another in the multi-dimensional feature-space can be thought of as super-features which were then used in developing the classifier rule set in eCognition. In this study, we report an overall classification accuracy of greater than 90% in different areas.

A real-time standard parts inspection based on deep learning

NASA Astrophysics Data System (ADS)

Xu, Kuan; Li, XuDong; Jiang, Hongzhi; Zhao, Huijie

2017-10-01

Since standard parts are necessary components in mechanical structure like bogie and connector. These mechanical structures will be shattered or loosen if standard parts are lost. So real-time standard parts inspection systems are essential to guarantee their safety. Researchers would like to take inspection systems based on deep learning because it works well in image with complex backgrounds which is common in standard parts inspection situation. A typical inspection detection system contains two basic components: feature extractors and object classifiers. For the object classifier, Region Proposal Network (RPN) is one of the most essential architectures in most state-of-art object detection systems. However, in the basic RPN architecture, the proposals of Region of Interest (ROI) have fixed sizes (9 anchors for each pixel), they are effective but they waste much computing resources and time. In standard parts detection situations, standard parts have given size, thus we can manually choose sizes of anchors based on the ground-truths through machine learning. The experiments prove that we could use 2 anchors to achieve almost the same accuracy and recall rate. Basically, our standard parts detection system could reach 15fps on NVIDIA GTX1080 (GPU), while achieving detection accuracy 90.01% mAP.

Prediction of troponin-T degradation using color image texture features in 10d aged beef longissimus steaks.

PubMed

Sun, X; Chen, K J; Berg, E P; Newman, D J; Schwartz, C A; Keller, W L; Maddock Carlin, K R

2014-02-01

The objective was to use digital color image texture features to predict troponin-T degradation in beef. Image texture features, including 88 gray level co-occurrence texture features, 81 two-dimension fast Fourier transformation texture features, and 48 Gabor wavelet filter texture features, were extracted from color images of beef strip steaks (longissimus dorsi, n = 102) aged for 10d obtained using a digital camera and additional lighting. Steaks were designated degraded or not-degraded based on troponin-T degradation determined on d 3 and d 10 postmortem by immunoblotting. Statistical analysis (STEPWISE regression model) and artificial neural network (support vector machine model, SVM) methods were designed to classify protein degradation. The d 3 and d 10 STEPWISE models were 94% and 86% accurate, respectively, while the d 3 and d 10 SVM models were 63% and 71%, respectively, in predicting protein degradation in aged meat. STEPWISE and SVM models based on image texture features show potential to predict troponin-T degradation in meat. © 2013.

Optimal classification for the diagnosis of duchenne muscular dystrophy images using support vector machines.

PubMed

Zhang, Ming-Huan; Ma, Jun-Shan; Shen, Ying; Chen, Ying

2016-09-01

This study aimed to investigate the optimal support vector machines (SVM)-based classifier of duchenne muscular dystrophy (DMD) magnetic resonance imaging (MRI) images. T1-weighted (T1W) and T2-weighted (T2W) images of the 15 boys with DMD and 15 normal controls were obtained. Textural features of the images were extracted and wavelet decomposed, and then, principal features were selected. Scale transform was then performed for MRI images. Afterward, SVM-based classifiers of MRI images were analyzed based on the radical basis function and decomposition levels. The cost (C) parameter and kernel parameter [Formula: see text] were used for classification. Then, the optimal SVM-based classifier, expressed as [Formula: see text]), was identified by performance evaluation (sensitivity, specificity and accuracy). Eight of 12 textural features were selected as principal features (eigenvalues [Formula: see text]). The 16 SVM-based classifiers were obtained using combination of (C, [Formula: see text]), and those with lower C and [Formula: see text] values showed higher performances, especially classifier of [Formula: see text]). The SVM-based classifiers of T1W images showed higher performance than T1W images at the same decomposition level. The T1W images in classifier of [Formula: see text]) at level 2 decomposition showed the highest performance of all, and its overall correct sensitivity, specificity, and accuracy reached 96.9, 97.3, and 97.1 %, respectively. The T1W images in SVM-based classifier [Formula: see text] at level 2 decomposition showed the highest performance of all, demonstrating that it was the optimal classification for the diagnosis of DMD.

Intratumor heterogeneity of DCE-MRI reveals Ki-67 proliferation status in breast cancer

NASA Astrophysics Data System (ADS)

Cheng, Hu; Fan, Ming; Zhang, Peng; Liu, Bin; Shao, Guoliang; Li, Lihua

2018-03-01

Breast cancer is a highly heterogeneous disease both biologically and clinically, and certain pathologic parameters, i.e., Ki67 expression, are useful in predicting the prognosis of patients. The aim of the study is to identify intratumor heterogeneity of breast cancer for predicting Ki-67 proliferation status in estrogen receptor (ER)-positive breast cancer patients. A dataset of 77 patients was collected who underwent dynamic contrast enhancement magnetic resonance imaging (DCE-MRI) examination. Of these patients, 51 were high-Ki-67 expression and 26 were low-Ki-67 expression. We partitioned the breast tumor into subregions using two methods based on the values of time to peak (TTP) and peak enhancement rate (PER). Within each tumor subregion, image features were extracted including statistical and morphological features from DCE-MRI. The classification models were applied on each region separately to assess whether the classifiers based on features extracted from various subregions features could have different performance for prediction. An area under a receiver operating characteristic curve (AUC) was computed using leave-one-out cross-validation (LOOCV) method. The classifier using features related with moderate time to peak achieved best performance with AUC of 0.826 than that based on the other regions. While using multi-classifier fusion method, the AUC value was significantly (P=0.03) increased to 0.858+/-0.032 compare to classifier with AUC of 0.778 using features from the entire tumor. The results demonstrated that features reflect heterogeneity in intratumoral subregions can improve the classifier performance to predict the Ki-67 proliferation status than the classifier using features from entire tumor alone.

Utilizing a structural meta-ontology for family-based quality assurance of the BioPortal ontologies.

PubMed

Ochs, Christopher; He, Zhe; Zheng, Ling; Geller, James; Perl, Yehoshua; Hripcsak, George; Musen, Mark A

2016-06-01

An Abstraction Network is a compact summary of an ontology's structure and content. In previous research, we showed that Abstraction Networks support quality assurance (QA) of biomedical ontologies. The development of an Abstraction Network and its associated QA methodologies, however, is a labor-intensive process that previously was applicable only to one ontology at a time. To improve the efficiency of the Abstraction-Network-based QA methodology, we introduced a QA framework that uses uniform Abstraction Network derivation techniques and QA methodologies that are applicable to whole families of structurally similar ontologies. For the family-based framework to be successful, it is necessary to develop a method for classifying ontologies into structurally similar families. We now describe a structural meta-ontology that classifies ontologies according to certain structural features that are commonly used in the modeling of ontologies (e.g., object properties) and that are important for Abstraction Network derivation. Each class of the structural meta-ontology represents a family of ontologies with identical structural features, indicating which types of Abstraction Networks and QA methodologies are potentially applicable to all of the ontologies in the family. We derive a collection of 81 families, corresponding to classes of the structural meta-ontology, that enable a flexible, streamlined family-based QA methodology, offering multiple choices for classifying an ontology. The structure of 373 ontologies from the NCBO BioPortal is analyzed and each ontology is classified into multiple families modeled by the structural meta-ontology. Copyright © 2016 Elsevier Inc. All rights reserved.

Automatic detection of red lesions in digital color fundus photographs.

PubMed

Niemeijer, Meindert; van Ginneken, Bram; Staal, Joes; Suttorp-Schulten, Maria S A; Abràmoff, Michael D

2005-05-01

The robust detection of red lesions in digital color fundus photographs is a critical step in the development of automated screening systems for diabetic retinopathy. In this paper, a novel red lesion detection method is presented based on a hybrid approach, combining prior works by Spencer et al. (1996) and Frame et al. (1998) with two important new contributions. The first contribution is a new red lesion candidate detection system based on pixel classification. Using this technique, vasculature and red lesions are separated from the background of the image. After removal of the connected vasculature the remaining objects are considered possible red lesions. Second, an extensive number of new features are added to those proposed by Spencer-Frame. The detected candidate objects are classified using all features and a k-nearest neighbor classifier. An extensive evaluation was performed on a test set composed of images representative of those normally found in a screening set. When determining whether an image contains red lesions the system achieves a sensitivity of 100% at a specificity of 87%. The method is compared with several different automatic systems and is shown to outperform them all. Performance is close to that of a human expert examining the images for the presence of red lesions.

A multispectral automatic target recognition application for maritime surveillance, search, and rescue

NASA Astrophysics Data System (ADS)

Schoonmaker, Jon; Reed, Scott; Podobna, Yuliya; Vazquez, Jose; Boucher, Cynthia

2010-04-01

Due to increased security concerns, the commitment to monitor and maintain security in the maritime environment is increasingly a priority. A country's coast is the most vulnerable area for the incursion of illegal immigrants, terrorists and contraband. This work illustrates the ability of a low-cost, light-weight, multi-spectral, multi-channel imaging system to handle the environment and see under difficult marine conditions. The system and its implemented detecting and tracking technologies should be organic to the maritime homeland security community for search and rescue, fisheries, defense, and law enforcement. It is tailored for airborne and ship based platforms to detect, track and monitor suspected objects (such as semi-submerged targets like marine mammals, vessels in distress, and drug smugglers). In this system, automated detection and tracking technology is used to detect, classify and localize potential threats or objects of interest within the imagery provided by the multi-spectral system. These algorithms process the sensor data in real time, thereby providing immediate feedback when features of interest have been detected. A supervised detection system based on Haar features and Cascade Classifiers is presented and results are provided on real data. The system is shown to be extendable and reusable for a variety of different applications.

Using multiple classifiers for predicting the risk of endovascular aortic aneurysm repair re-intervention through hybrid feature selection.

PubMed

Attallah, Omneya; Karthikesalingam, Alan; Holt, Peter Je; Thompson, Matthew M; Sayers, Rob; Bown, Matthew J; Choke, Eddie C; Ma, Xianghong

2017-11-01

Feature selection is essential in medical area; however, its process becomes complicated with the presence of censoring which is the unique character of survival analysis. Most survival feature selection methods are based on Cox's proportional hazard model, though machine learning classifiers are preferred. They are less employed in survival analysis due to censoring which prevents them from directly being used to survival data. Among the few work that employed machine learning classifiers, partial logistic artificial neural network with auto-relevance determination is a well-known method that deals with censoring and perform feature selection for survival data. However, it depends on data replication to handle censoring which leads to unbalanced and biased prediction results especially in highly censored data. Other methods cannot deal with high censoring. Therefore, in this article, a new hybrid feature selection method is proposed which presents a solution to high level censoring. It combines support vector machine, neural network, and K-nearest neighbor classifiers using simple majority voting and a new weighted majority voting method based on survival metric to construct a multiple classifier system. The new hybrid feature selection process uses multiple classifier system as a wrapper method and merges it with iterated feature ranking filter method to further reduce features. Two endovascular aortic repair datasets containing 91% censored patients collected from two centers were used to construct a multicenter study to evaluate the performance of the proposed approach. The results showed the proposed technique outperformed individual classifiers and variable selection methods based on Cox's model such as Akaike and Bayesian information criterions and least absolute shrinkage and selector operator in p values of the log-rank test, sensitivity, and concordance index. This indicates that the proposed classifier is more powerful in correctly predicting the risk of re-intervention enabling doctor in selecting patients' future follow-up plan.

MODAL TRACKING of A Structural Device: A Subspace Identification Approach

DOE Office of Scientific and Technical Information (OSTI.GOV)

Candy, J. V.; Franco, S. N.; Ruggiero, E. L.

Mechanical devices operating in an environment contaminated by noise, uncertainties, and extraneous disturbances lead to low signal-to-noise-ratios creating an extremely challenging processing problem. To detect/classify a device subsystem from noisy data, it is necessary to identify unique signatures or particular features. An obvious feature would be resonant (modal) frequencies emitted during its normal operation. In this report, we discuss a model-based approach to incorporate these physical features into a dynamic structure that can be used for such an identification. The approach we take after pre-processing the raw vibration data and removing any extraneous disturbances is to obtain a representation ofmore » the structurally unknown device along with its subsystems that capture these salient features. One approach is to recognize that unique modal frequencies (sinusoidal lines) appear in the estimated power spectrum that are solely characteristic of the device under investigation. Therefore, the objective of this effort is based on constructing a black box model of the device that captures these physical features that can be exploited to “diagnose” whether or not the particular device subsystem (track/detect/classify) is operating normally from noisy vibrational data. Here we discuss the application of a modern system identification approach based on stochastic subspace realization techniques capable of both (1) identifying the underlying black-box structure thereby enabling the extraction of structural modes that can be used for analysis and modal tracking as well as (2) indicators of condition and possible changes from normal operation.« less

Normed kernel function-based fuzzy possibilistic C-means (NKFPCM) algorithm for high-dimensional breast cancer database classification with feature selection is based on Laplacian Score

NASA Astrophysics Data System (ADS)

Lestari, A. W.; Rustam, Z.

2017-07-01

In the last decade, breast cancer has become the focus of world attention as this disease is one of the primary leading cause of death for women. Therefore, it is necessary to have the correct precautions and treatment. In previous studies, Fuzzy Kennel K-Medoid algorithm has been used for multi-class data. This paper proposes an algorithm to classify the high dimensional data of breast cancer using Fuzzy Possibilistic C-means (FPCM) and a new method based on clustering analysis using Normed Kernel Function-Based Fuzzy Possibilistic C-Means (NKFPCM). The objective of this paper is to obtain the best accuracy in classification of breast cancer data. In order to improve the accuracy of the two methods, the features candidates are evaluated using feature selection, where Laplacian Score is used. The results show the comparison accuracy and running time of FPCM and NKFPCM with and without feature selection.

Feature selection and classification of multiparametric medical images using bagging and SVM

NASA Astrophysics Data System (ADS)

Fan, Yong; Resnick, Susan M.; Davatzikos, Christos

2008-03-01

This paper presents a framework for brain classification based on multi-parametric medical images. This method takes advantage of multi-parametric imaging to provide a set of discriminative features for classifier construction by using a regional feature extraction method which takes into account joint correlations among different image parameters; in the experiments herein, MRI and PET images of the brain are used. Support vector machine classifiers are then trained based on the most discriminative features selected from the feature set. To facilitate robust classification and optimal selection of parameters involved in classification, in view of the well-known "curse of dimensionality", base classifiers are constructed in a bagging (bootstrap aggregating) framework for building an ensemble classifier and the classification parameters of these base classifiers are optimized by means of maximizing the area under the ROC (receiver operating characteristic) curve estimated from their prediction performance on left-out samples of bootstrap sampling. This classification system is tested on a sex classification problem, where it yields over 90% classification rates for unseen subjects. The proposed classification method is also compared with other commonly used classification algorithms, with favorable results. These results illustrate that the methods built upon information jointly extracted from multi-parametric images have the potential to perform individual classification with high sensitivity and specificity.

Chaotic Particle Swarm Optimization with Mutation for Classification

PubMed Central

Assarzadeh, Zahra; Naghsh-Nilchi, Ahmad Reza

2015-01-01

In this paper, a chaotic particle swarm optimization with mutation-based classifier particle swarm optimization is proposed to classify patterns of different classes in the feature space. The introduced mutation operators and chaotic sequences allows us to overcome the problem of early convergence into a local minima associated with particle swarm optimization algorithms. That is, the mutation operator sharpens the convergence and it tunes the best possible solution. Furthermore, to remove the irrelevant data and reduce the dimensionality of medical datasets, a feature selection approach using binary version of the proposed particle swarm optimization is introduced. In order to demonstrate the effectiveness of our proposed classifier, mutation-based classifier particle swarm optimization, it is checked out with three sets of data classifications namely, Wisconsin diagnostic breast cancer, Wisconsin breast cancer and heart-statlog, with different feature vector dimensions. The proposed algorithm is compared with different classifier algorithms including k-nearest neighbor, as a conventional classifier, particle swarm-classifier, genetic algorithm, and Imperialist competitive algorithm-classifier, as more sophisticated ones. The performance of each classifier was evaluated by calculating the accuracy, sensitivity, specificity and Matthews's correlation coefficient. The experimental results show that the mutation-based classifier particle swarm optimization unequivocally performs better than all the compared algorithms. PMID:25709937

A random forest model based classification scheme for neonatal amplitude-integrated EEG.

PubMed

Chen, Weiting; Wang, Yu; Cao, Guitao; Chen, Guoqiang; Gu, Qiufang

2014-01-01

Modern medical advances have greatly increased the survival rate of infants, while they remain in the higher risk group for neurological problems later in life. For the infants with encephalopathy or seizures, identification of the extent of brain injury is clinically challenging. Continuous amplitude-integrated electroencephalography (aEEG) monitoring offers a possibility to directly monitor the brain functional state of the newborns over hours, and has seen an increasing application in neonatal intensive care units (NICUs). This paper presents a novel combined feature set of aEEG and applies random forest (RF) method to classify aEEG tracings. To that end, a series of experiments were conducted on 282 aEEG tracing cases (209 normal and 73 abnormal ones). Basic features, statistic features and segmentation features were extracted from both the tracing as a whole and the segmented recordings, and then form a combined feature set. All the features were sent to a classifier afterwards. The significance of feature, the data segmentation, the optimization of RF parameters, and the problem of imbalanced datasets were examined through experiments. Experiments were also done to evaluate the performance of RF on aEEG signal classifying, compared with several other widely used classifiers including SVM-Linear, SVM-RBF, ANN, Decision Tree (DT), Logistic Regression(LR), ML, and LDA. The combined feature set can better characterize aEEG signals, compared with basic features, statistic features and segmentation features respectively. With the combined feature set, the proposed RF-based aEEG classification system achieved a correct rate of 92.52% and a high F1-score of 95.26%. Among all of the seven classifiers examined in our work, the RF method got the highest correct rate, sensitivity, specificity, and F1-score, which means that RF outperforms all of the other classifiers considered here. The results show that the proposed RF-based aEEG classification system with the combined feature set is efficient and helpful to better detect the brain disorders in newborns.

Earthquake Damage Assessment over Port-au-Prince (Haiti) by Fusing Optical and SAR Data

NASA Astrophysics Data System (ADS)

Romaniello, V.; Piscini, A.; Bignami, C.; Anniballe, R.; Pierdicca, N.; Stramondo, S.

2016-08-01

This work proposes methodologies aiming at evaluating the sensitivity of optical and SAR change features obtained from satellite images with respect to the damage grade. The proposed methods are derived from the literature ([1], [2], [3], [4]) and the main novelty concerns the estimation of these change features at object scale.The test case is the Mw 7.0 earthquake that hit Haiti on January 12, 2010.The analysis of change detection indicators is based on ground truth information collected during a post- earthquake survey. We have generated the damage map of Port-au-Prince by considering a set of polygons extracted from the open source Open Street Map geo- database. The resulting damage map was calculated in terms of collapse ratio [5].We selected some features having a good sensitivity with damage at object scale [6]: the Normalised Difference Index, the Kullback-Libler Divergence, the Mutual Information and the Intensity Correlation Difference.The Naive Bayes and the Support Vector Machine classifiers were used to evaluate the goodness of these features. The classification results demonstrate that the simultaneous use of several change features from EO observations can improve the damage estimation at object scale.

Fully Connected Cascade Artificial Neural Network Architecture for Attention Deficit Hyperactivity Disorder Classification From Functional Magnetic Resonance Imaging Data.

PubMed

Deshpande, Gopikrishna; Wang, Peng; Rangaprakash, D; Wilamowski, Bogdan

2015-12-01

Automated recognition and classification of brain diseases are of tremendous value to society. Attention deficit hyperactivity disorder (ADHD) is a diverse spectrum disorder whose diagnosis is based on behavior and hence will benefit from classification utilizing objective neuroimaging measures. Toward this end, an international competition was conducted for classifying ADHD using functional magnetic resonance imaging data acquired from multiple sites worldwide. Here, we consider the data from this competition as an example to illustrate the utility of fully connected cascade (FCC) artificial neural network (ANN) architecture for performing classification. We employed various directional and nondirectional brain connectivity-based methods to extract discriminative features which gave better classification accuracy compared to raw data. Our accuracy for distinguishing ADHD from healthy subjects was close to 90% and between the ADHD subtypes was close to 95%. Further, we show that, if properly used, FCC ANN performs very well compared to other classifiers such as support vector machines in terms of accuracy, irrespective of the feature used. Finally, the most discriminative connectivity features provided insights about the pathophysiology of ADHD and showed reduced and altered connectivity involving the left orbitofrontal cortex and various cerebellar regions in ADHD.

A novel approach for detection and classification of mammographic microcalcifications using wavelet analysis and extreme learning machine.

PubMed

Malar, E; Kandaswamy, A; Chakravarthy, D; Giri Dharan, A

2012-09-01

The objective of this paper is to reveal the effectiveness of wavelet based tissue texture analysis for microcalcification detection in digitized mammograms using Extreme Learning Machine (ELM). Microcalcifications are tiny deposits of calcium in the breast tissue which are potential indicators for early detection of breast cancer. The dense nature of the breast tissue and the poor contrast of the mammogram image prohibit the effectiveness in identifying microcalcifications. Hence, a new approach to discriminate the microcalcifications from the normal tissue is done using wavelet features and is compared with different feature vectors extracted using Gray Level Spatial Dependence Matrix (GLSDM) and Gabor filter based techniques. A total of 120 Region of Interests (ROIs) extracted from 55 mammogram images of mini-Mias database, including normal and microcalcification images are used in the current research. The network is trained with the above mentioned features and the results denote that ELM produces relatively better classification accuracy (94%) with a significant reduction in training time than the other artificial neural networks like Bayesnet classifier, Naivebayes classifier, and Support Vector Machine. ELM also avoids problems like local minima, improper learning rate, and over fitting. Copyright © 2012 Elsevier Ltd. All rights reserved.

A Deep Convolutional Neural Network for segmenting and classifying epithelial and stromal regions in histopathological images

PubMed Central

Xu, Jun; Luo, Xiaofei; Wang, Guanhao; Gilmore, Hannah; Madabhushi, Anant

2016-01-01

Epithelial (EP) and stromal (ST) are two types of tissues in histological images. Automated segmentation or classification of EP and ST tissues is important when developing computerized system for analyzing the tumor microenvironment. In this paper, a Deep Convolutional Neural Networks (DCNN) based feature learning is presented to automatically segment or classify EP and ST regions from digitized tumor tissue microarrays (TMAs). Current approaches are based on handcraft feature representation, such as color, texture, and Local Binary Patterns (LBP) in classifying two regions. Compared to handcrafted feature based approaches, which involve task dependent representation, DCNN is an end-to-end feature extractor that may be directly learned from the raw pixel intensity value of EP and ST tissues in a data driven fashion. These high-level features contribute to the construction of a supervised classifier for discriminating the two types of tissues. In this work we compare DCNN based models with three handcraft feature extraction based approaches on two different datasets which consist of 157 Hematoxylin and Eosin (H&E) stained images of breast cancer and 1376 immunohistological (IHC) stained images of colorectal cancer, respectively. The DCNN based feature learning approach was shown to have a F1 classification score of 85%, 89%, and 100%, accuracy (ACC) of 84%, 88%, and 100%, and Matthews Correlation Coefficient (MCC) of 86%, 77%, and 100% on two H&E stained (NKI and VGH) and IHC stained data, respectively. Our DNN based approach was shown to outperform three handcraft feature extraction based approaches in terms of the classification of EP and ST regions. PMID:28154470

A Deep Convolutional Neural Network for segmenting and classifying epithelial and stromal regions in histopathological images.

PubMed

Xu, Jun; Luo, Xiaofei; Wang, Guanhao; Gilmore, Hannah; Madabhushi, Anant

2016-05-26

Epithelial (EP) and stromal (ST) are two types of tissues in histological images. Automated segmentation or classification of EP and ST tissues is important when developing computerized system for analyzing the tumor microenvironment. In this paper, a Deep Convolutional Neural Networks (DCNN) based feature learning is presented to automatically segment or classify EP and ST regions from digitized tumor tissue microarrays (TMAs). Current approaches are based on handcraft feature representation, such as color, texture, and Local Binary Patterns (LBP) in classifying two regions. Compared to handcrafted feature based approaches, which involve task dependent representation, DCNN is an end-to-end feature extractor that may be directly learned from the raw pixel intensity value of EP and ST tissues in a data driven fashion. These high-level features contribute to the construction of a supervised classifier for discriminating the two types of tissues. In this work we compare DCNN based models with three handcraft feature extraction based approaches on two different datasets which consist of 157 Hematoxylin and Eosin (H&E) stained images of breast cancer and 1376 immunohistological (IHC) stained images of colorectal cancer, respectively. The DCNN based feature learning approach was shown to have a F1 classification score of 85%, 89%, and 100%, accuracy (ACC) of 84%, 88%, and 100%, and Matthews Correlation Coefficient (MCC) of 86%, 77%, and 100% on two H&E stained (NKI and VGH) and IHC stained data, respectively. Our DNN based approach was shown to outperform three handcraft feature extraction based approaches in terms of the classification of EP and ST regions.

Deep convolutional neural networks for classifying GPR B-scans

NASA Astrophysics Data System (ADS)

Besaw, Lance E.; Stimac, Philip J.

2015-05-01

Symmetric and asymmetric buried explosive hazards (BEHs) present real, persistent, deadly threats on the modern battlefield. Current approaches to mitigate these threats rely on highly trained operatives to reliably detect BEHs with reasonable false alarm rates using handheld Ground Penetrating Radar (GPR) and metal detectors. As computers become smaller, faster and more efficient, there exists greater potential for automated threat detection based on state-of-the-art machine learning approaches, reducing the burden on the field operatives. Recent advancements in machine learning, specifically deep learning artificial neural networks, have led to significantly improved performance in pattern recognition tasks, such as object classification in digital images. Deep convolutional neural networks (CNNs) are used in this work to extract meaningful signatures from 2-dimensional (2-D) GPR B-scans and classify threats. The CNNs skip the traditional "feature engineering" step often associated with machine learning, and instead learn the feature representations directly from the 2-D data. A multi-antennae, handheld GPR with centimeter-accurate positioning data was used to collect shallow subsurface data over prepared lanes containing a wide range of BEHs. Several heuristics were used to prevent over-training, including cross validation, network weight regularization, and "dropout." Our results show that CNNs can extract meaningful features and accurately classify complex signatures contained in GPR B-scans, complementing existing GPR feature extraction and classification techniques.

Driving behavior recognition using EEG data from a simulated car-following experiment.

PubMed

Yang, Liu; Ma, Rui; Zhang, H Michael; Guan, Wei; Jiang, Shixiong

2018-07-01

Driving behavior recognition is the foundation of driver assistance systems, with potential applications in automated driving systems. Most prevailing studies have used subjective questionnaire data and objective driving data to classify driving behaviors, while few studies have used physiological signals such as electroencephalography (EEG) to gather data. To bridge this gap, this paper proposes a two-layer learning method for driving behavior recognition using EEG data. A simulated car-following driving experiment was designed and conducted to simultaneously collect data on the driving behaviors and EEG data of drivers. The proposed learning method consists of two layers. In Layer I, two-dimensional driving behavior features representing driving style and stability were selected and extracted from raw driving behavior data using K-means and support vector machine recursive feature elimination. Five groups of driving behaviors were classified based on these two-dimensional driving behavior features. In Layer II, the classification results from Layer I were utilized as inputs to generate a k-Nearest-Neighbor classifier identifying driving behavior groups using EEG data. Using independent component analysis, a fast Fourier transformation, and linear discriminant analysis sequentially, the raw EEG signals were processed to extract two core EEG features. Classifier performance was enhanced using the adaptive synthetic sampling approach. A leave-one-subject-out cross validation was conducted. The results showed that the average classification accuracy for all tested traffic states was 69.5% and the highest accuracy reached 83.5%, suggesting a significant correlation between EEG patterns and car-following behavior. Copyright © 2017 Elsevier Ltd. All rights reserved.

Image Augmentation for Object Image Classification Based On Combination of Pre-Trained CNN and SVM

NASA Astrophysics Data System (ADS)

Shima, Yoshihiro

2018-04-01

Neural networks are a powerful means of classifying object images. The proposed image category classification method for object images combines convolutional neural networks (CNNs) and support vector machines (SVMs). A pre-trained CNN, called Alex-Net, is used as a pattern-feature extractor. Alex-Net is pre-trained for the large-scale object-image dataset ImageNet. Instead of training, Alex-Net, pre-trained for ImageNet is used. An SVM is used as trainable classifier. The feature vectors are passed to the SVM from Alex-Net. The STL-10 dataset are used as object images. The number of classes is ten. Training and test samples are clearly split. STL-10 object images are trained by the SVM with data augmentation. We use the pattern transformation method with the cosine function. We also apply some augmentation method such as rotation, skewing and elastic distortion. By using the cosine function, the original patterns were left-justified, right-justified, top-justified, or bottom-justified. Patterns were also center-justified and enlarged. Test error rate is decreased by 0.435 percentage points from 16.055% by augmentation with cosine transformation. Error rates are increased by other augmentation method such as rotation, skewing and elastic distortion, compared without augmentation. Number of augmented data is 30 times that of the original STL-10 5K training samples. Experimental test error rate for the test 8k STL-10 object images was 15.620%, which shows that image augmentation is effective for image category classification.

Automatic seizure detection based on the combination of newborn multi-channel EEG and HRV information

NASA Astrophysics Data System (ADS)

Mesbah, Mostefa; Balakrishnan, Malarvili; Colditz, Paul B.; Boashash, Boualem

2012-12-01

This article proposes a new method for newborn seizure detection that uses information extracted from both multi-channel electroencephalogram (EEG) and a single channel electrocardiogram (ECG). The aim of the study is to assess whether additional information extracted from ECG can improve the performance of seizure detectors based solely on EEG. Two different approaches were used to combine this extracted information. The first approach, known as feature fusion, involves combining features extracted from EEG and heart rate variability (HRV) into a single feature vector prior to feeding it to a classifier. The second approach, called classifier or decision fusion, is achieved by combining the independent decisions of the EEG and the HRV-based classifiers. Tested on recordings obtained from eight newborns with identified EEG seizures, the proposed neonatal seizure detection algorithms achieved 95.20% sensitivity and 88.60% specificity for the feature fusion case and 95.20% sensitivity and 94.30% specificity for the classifier fusion case. These results are considerably better than those involving classifiers using EEG only (80.90%, 86.50%) or HRV only (85.70%, 84.60%).

Diagnosis of the OCD Patients using Drawing Features of the Bender Gestalt Shapes

PubMed Central

Boostani, R.; Asadi, F.; Mohammadi, N.

2017-01-01

Background: Since psychological tests such as questionnaire or drawing tests are almost qualitative, their results carry a degree of uncertainty and sometimes subjectivity. The deficiency of all drawing tests is that the assessment is carried out after drawing the objects and lots of information such as pen angle, speed, curvature and pressure are missed through the test. In other words, the psychologists cannot assess their patients while running the tests. One of the famous drawing tests to measure the degree of Obsession Compulsion Disorder (OCD) is the Bender Gestalt, though its reliability is not promising. Objective: The main objective of this study is to make the Bender Gestalt test quantitative; therefore, an optical pen along with a digital tablet is utilized to preserve the key drawing features of OCD patients during the test. Materials and Methods: Among a large population of patients who referred to a special clinic of OCD, 50 under therapy subjects voluntarily took part in this study. In contrast, 50 subjects with no sign of OCD performed the test as a control group. This test contains 9 shapes and the participants were not constraint to draw the shapes in a certain interval of time; consequently, to classify the stream of feature vectors (samples through drawing) Hidden Markov Model (HMM) is employed and its flexibility increased by incorporating the fuzzy technique into its learning scheme. Results: Applying fuzzy HMM classifier to the data stream of subjects could classify two groups up to 95.2% accuracy, whereas the results by applying the standard HMM resulted in 94.5%. In addition, multi-layer perceptron (MLP), as a strong static classifier, is applied to the features and resulted in 86.6% accuracy. Conclusion: Applying the pair of T-test to the results implies a significant supremacy of the fuzzy HMM to the standard HMM and MLP classifiers. PMID:28462208

Application of texture analysis method for mammogram density classification

NASA Astrophysics Data System (ADS)

Nithya, R.; Santhi, B.

2017-07-01

Mammographic density is considered a major risk factor for developing breast cancer. This paper proposes an automated approach to classify breast tissue types in digital mammogram. The main objective of the proposed Computer-Aided Diagnosis (CAD) system is to investigate various feature extraction methods and classifiers to improve the diagnostic accuracy in mammogram density classification. Texture analysis methods are used to extract the features from the mammogram. Texture features are extracted by using histogram, Gray Level Co-Occurrence Matrix (GLCM), Gray Level Run Length Matrix (GLRLM), Gray Level Difference Matrix (GLDM), Local Binary Pattern (LBP), Entropy, Discrete Wavelet Transform (DWT), Wavelet Packet Transform (WPT), Gabor transform and trace transform. These extracted features are selected using Analysis of Variance (ANOVA). The features selected by ANOVA are fed into the classifiers to characterize the mammogram into two-class (fatty/dense) and three-class (fatty/glandular/dense) breast density classification. This work has been carried out by using the mini-Mammographic Image Analysis Society (MIAS) database. Five classifiers are employed namely, Artificial Neural Network (ANN), Linear Discriminant Analysis (LDA), Naive Bayes (NB), K-Nearest Neighbor (KNN), and Support Vector Machine (SVM). Experimental results show that ANN provides better performance than LDA, NB, KNN and SVM classifiers. The proposed methodology has achieved 97.5% accuracy for three-class and 99.37% for two-class density classification.

Texture- and deformability-based surface recognition by tactile image analysis.

PubMed

Khasnobish, Anwesha; Pal, Monalisa; Tibarewala, D N; Konar, Amit; Pal, Kunal

2016-08-01

Deformability and texture are two unique object characteristics which are essential for appropriate surface recognition by tactile exploration. Tactile sensation is required to be incorporated in artificial arms for rehabilitative and other human-computer interface applications to achieve efficient and human-like manoeuvring. To accomplish the same, surface recognition by tactile data analysis is one of the prerequisites. The aim of this work is to develop effective technique for identification of various surfaces based on deformability and texture by analysing tactile images which are obtained during dynamic exploration of the item by artificial arms whose gripper is fitted with tactile sensors. Tactile data have been acquired, while human beings as well as a robot hand fitted with tactile sensors explored the objects. The tactile images are pre-processed, and relevant features are extracted from the tactile images. These features are provided as input to the variants of support vector machine (SVM), linear discriminant analysis and k-nearest neighbour (kNN) for classification. Based on deformability, six household surfaces are recognized from their corresponding tactile images. Moreover, based on texture five surfaces of daily use are classified. The method adopted in the former two cases has also been applied for deformability- and texture-based recognition of four biomembranes, i.e. membranes prepared from biomaterials which can be used for various applications such as drug delivery and implants. Linear SVM performed best for recognizing surface deformability with an accuracy of 83 % in 82.60 ms, whereas kNN classifier recognizes surfaces of daily use having different textures with an accuracy of 89 % in 54.25 ms and SVM with radial basis function kernel recognizes biomembranes with an accuracy of 78 % in 53.35 ms. The classifiers are observed to generalize well on the unseen test datasets with very high performance to achieve efficient material recognition based on its deformability and texture.

An ensemble method for extracting adverse drug events from social media.

PubMed

Liu, Jing; Zhao, Songzheng; Zhang, Xiaodi

2016-06-01

Because adverse drug events (ADEs) are a serious health problem and a leading cause of death, it is of vital importance to identify them correctly and in a timely manner. With the development of Web 2.0, social media has become a large data source for information on ADEs. The objective of this study is to develop a relation extraction system that uses natural language processing techniques to effectively distinguish between ADEs and non-ADEs in informal text on social media. We develop a feature-based approach that utilizes various lexical, syntactic, and semantic features. Information-gain-based feature selection is performed to address high-dimensional features. Then, we evaluate the effectiveness of four well-known kernel-based approaches (i.e., subset tree kernel, tree kernel, shortest dependency path kernel, and all-paths graph kernel) and several ensembles that are generated by adopting different combination methods (i.e., majority voting, weighted averaging, and stacked generalization). All of the approaches are tested using three data sets: two health-related discussion forums and one general social networking site (i.e., Twitter). When investigating the contribution of each feature subset, the feature-based approach attains the best area under the receiver operating characteristics curve (AUC) values, which are 78.6%, 72.2%, and 79.2% on the three data sets. When individual methods are used, we attain the best AUC values of 82.1%, 73.2%, and 77.0% using the subset tree kernel, shortest dependency path kernel, and feature-based approach on the three data sets, respectively. When using classifier ensembles, we achieve the best AUC values of 84.5%, 77.3%, and 84.5% on the three data sets, outperforming the baselines. Our experimental results indicate that ADE extraction from social media can benefit from feature selection. With respect to the effectiveness of different feature subsets, lexical features and semantic features can enhance the ADE extraction capability. Kernel-based approaches, which can stay away from the feature sparsity issue, are qualified to address the ADE extraction problem. Combining different individual classifiers using suitable combination methods can further enhance the ADE extraction effectiveness. Copyright © 2016 Elsevier B.V. All rights reserved.

Combined texture feature analysis of segmentation and classification of benign and malignant tumour CT slices.

PubMed

Padma, A; Sukanesh, R

2013-01-01

A computer software system is designed for the segmentation and classification of benign from malignant tumour slices in brain computed tomography (CT) images. This paper presents a method to find and select both the dominant run length and co-occurrence texture features of region of interest (ROI) of the tumour region of each slice to be segmented by Fuzzy c means clustering (FCM) and evaluate the performance of support vector machine (SVM)-based classifiers in classifying benign and malignant tumour slices. Two hundred and six tumour confirmed CT slices are considered in this study. A total of 17 texture features are extracted by a feature extraction procedure, and six features are selected using Principal Component Analysis (PCA). This study constructed the SVM-based classifier with the selected features and by comparing the segmentation results with the experienced radiologist labelled ground truth (target). Quantitative analysis between ground truth and segmented tumour is presented in terms of segmentation accuracy, segmentation error and overlap similarity measures such as the Jaccard index. The classification performance of the SVM-based classifier with the same selected features is also evaluated using a 10-fold cross-validation method. The proposed system provides some newly found texture features have an important contribution in classifying benign and malignant tumour slices efficiently and accurately with less computational time. The experimental results showed that the proposed system is able to achieve the highest segmentation and classification accuracy effectiveness as measured by jaccard index and sensitivity and specificity.

Uncertain Classification of Variable Stars: Handling Observational GAPS and Noise

NASA Astrophysics Data System (ADS)

Castro, Nicolás; Protopapas, Pavlos; Pichara, Karim

2018-01-01

Automatic classification methods applied to sky surveys have revolutionized the astronomical target selection process. Most surveys generate a vast amount of time series, or “lightcurves,” that represent the brightness variability of stellar objects in time. Unfortunately, lightcurves’ observations take several years to be completed, producing truncated time series that generally remain without the application of automatic classifiers until they are finished. This happens because state-of-the-art methods rely on a variety of statistical descriptors or features that present an increasing degree of dispersion when the number of observations decreases, which reduces their precision. In this paper, we propose a novel method that increases the performance of automatic classifiers of variable stars by incorporating the deviations that scarcity of observations produces. Our method uses Gaussian process regression to form a probabilistic model of each lightcurve’s observations. Then, based on this model, bootstrapped samples of the time series features are generated. Finally, a bagging approach is used to improve the overall performance of the classification. We perform tests on the MAssive Compact Halo Object (MACHO) and Optical Gravitational Lensing Experiment (OGLE) catalogs, results show that our method effectively classifies some variability classes using a small fraction of the original observations. For example, we found that RR Lyrae stars can be classified with ~80% accuracy just by observing the first 5% of the whole lightcurves’ observations in the MACHO and OGLE catalogs. We believe these results prove that, when studying lightcurves, it is important to consider the features’ error and how the measurement process impacts it.

The DTW-based representation space for seismic pattern classification

NASA Astrophysics Data System (ADS)

Orozco-Alzate, Mauricio; Castro-Cabrera, Paola Alexandra; Bicego, Manuele; Londoño-Bonilla, John Makario

2015-12-01

Distinguishing among the different seismic volcanic patterns is still one of the most important and labor-intensive tasks for volcano monitoring. This task could be lightened and made free from subjective bias by using automatic classification techniques. In this context, a core but often overlooked issue is the choice of an appropriate representation of the data to be classified. Recently, it has been suggested that using a relative representation (i.e. proximities, namely dissimilarities on pairs of objects) instead of an absolute one (i.e. features, namely measurements on single objects) is advantageous to exploit the relational information contained in the dissimilarities to derive highly discriminant vector spaces, where any classifier can be used. According to that motivation, this paper investigates the suitability of a dynamic time warping (DTW) dissimilarity-based vector representation for the classification of seismic patterns. Results show the usefulness of such a representation in the seismic pattern classification scenario, including analyses of potential benefits from recent advances in the dissimilarity-based paradigm such as the proper selection of representation sets and the combination of different dissimilarity representations that might be available for the same data.

Classification of clinically useful sentences in clinical evidence resources.

PubMed

Morid, Mohammad Amin; Fiszman, Marcelo; Raja, Kalpana; Jonnalagadda, Siddhartha R; Del Fiol, Guilherme

2016-04-01

Most patient care questions raised by clinicians can be answered by online clinical knowledge resources. However, important barriers still challenge the use of these resources at the point of care. To design and assess a method for extracting clinically useful sentences from synthesized online clinical resources that represent the most clinically useful information for directly answering clinicians' information needs. We developed a Kernel-based Bayesian Network classification model based on different domain-specific feature types extracted from sentences in a gold standard composed of 18 UpToDate documents. These features included UMLS concepts and their semantic groups, semantic predications extracted by SemRep, patient population identified by a pattern-based natural language processing (NLP) algorithm, and cue words extracted by a feature selection technique. Algorithm performance was measured in terms of precision, recall, and F-measure. The feature-rich approach yielded an F-measure of 74% versus 37% for a feature co-occurrence method (p<0.001). Excluding predication, population, semantic concept or text-based features reduced the F-measure to 62%, 66%, 58% and 69% respectively (p<0.01). The classifier applied to Medline sentences reached an F-measure of 73%, which is equivalent to the performance of the classifier on UpToDate sentences (p=0.62). The feature-rich approach significantly outperformed general baseline methods. This approach significantly outperformed classifiers based on a single type of feature. Different types of semantic features provided a unique contribution to overall classification performance. The classifier's model and features used for UpToDate generalized well to Medline abstracts. Copyright © 2016 Elsevier Inc. All rights reserved.

Joint Feature Extraction and Classifier Design for ECG-Based Biometric Recognition.

PubMed

Gutta, Sandeep; Cheng, Qi

2016-03-01

Traditional biometric recognition systems often utilize physiological traits such as fingerprint, face, iris, etc. Recent years have seen a growing interest in electrocardiogram (ECG)-based biometric recognition techniques, especially in the field of clinical medicine. In existing ECG-based biometric recognition methods, feature extraction and classifier design are usually performed separately. In this paper, a multitask learning approach is proposed, in which feature extraction and classifier design are carried out simultaneously. Weights are assigned to the features within the kernel of each task. We decompose the matrix consisting of all the feature weights into sparse and low-rank components. The sparse component determines the features that are relevant to identify each individual, and the low-rank component determines the common feature subspace that is relevant to identify all the subjects. A fast optimization algorithm is developed, which requires only the first-order information. The performance of the proposed approach is demonstrated through experiments using the MIT-BIH Normal Sinus Rhythm database.

Detection of Epileptic Seizure Event and Onset Using EEG

PubMed Central

Ahammad, Nabeel; Fathima, Thasneem; Joseph, Paul

2014-01-01

This study proposes a method of automatic detection of epileptic seizure event and onset using wavelet based features and certain statistical features without wavelet decomposition. Normal and epileptic EEG signals were classified using linear classifier. For seizure event detection, Bonn University EEG database has been used. Three types of EEG signals (EEG signal recorded from healthy volunteer with eye open, epilepsy patients in the epileptogenic zone during a seizure-free interval, and epilepsy patients during epileptic seizures) were classified. Important features such as energy, entropy, standard deviation, maximum, minimum, and mean at different subbands were computed and classification was done using linear classifier. The performance of classifier was determined in terms of specificity, sensitivity, and accuracy. The overall accuracy was 84.2%. In the case of seizure onset detection, the database used is CHB-MIT scalp EEG database. Along with wavelet based features, interquartile range (IQR) and mean absolute deviation (MAD) without wavelet decomposition were extracted. Latency was used to study the performance of seizure onset detection. Classifier gave a sensitivity of 98.5% with an average latency of 1.76 seconds. PMID:24616892

Research on Remote Sensing Geological Information Extraction Based on Object Oriented Classification

NASA Astrophysics Data System (ADS)

Gao, Hui

2018-04-01

The northern Tibet belongs to the Sub cold arid climate zone in the plateau. It is rarely visited by people. The geological working conditions are very poor. However, the stratum exposures are good and human interference is very small. Therefore, the research on the automatic classification and extraction of remote sensing geological information has typical significance and good application prospect. Based on the object-oriented classification in Northern Tibet, using the Worldview2 high-resolution remote sensing data, combined with the tectonic information and image enhancement, the lithological spectral features, shape features, spatial locations and topological relations of various geological information are excavated. By setting the threshold, based on the hierarchical classification, eight kinds of geological information were classified and extracted. Compared with the existing geological maps, the accuracy analysis shows that the overall accuracy reached 87.8561 %, indicating that the classification-oriented method is effective and feasible for this study area and provides a new idea for the automatic extraction of remote sensing geological information.

A Tissue Systems Pathology Assay for High-Risk Barrett's Esophagus.

PubMed

Critchley-Thorne, Rebecca J; Duits, Lucas C; Prichard, Jeffrey W; Davison, Jon M; Jobe, Blair A; Campbell, Bruce B; Zhang, Yi; Repa, Kathleen A; Reese, Lia M; Li, Jinhong; Diehl, David L; Jhala, Nirag C; Ginsberg, Gregory; DeMarshall, Maureen; Foxwell, Tyler; Zaidi, Ali H; Lansing Taylor, D; Rustgi, Anil K; Bergman, Jacques J G H M; Falk, Gary W

2016-06-01

Better methods are needed to predict risk of progression for Barrett's esophagus. We aimed to determine whether a tissue systems pathology approach could predict progression in patients with nondysplastic Barrett's esophagus, indefinite for dysplasia, or low-grade dysplasia. We performed a nested case-control study to develop and validate a test that predicts progression of Barrett's esophagus to high-grade dysplasia (HGD) or esophageal adenocarcinoma (EAC), based upon quantification of epithelial and stromal variables in baseline biopsies. Data were collected from Barrett's esophagus patients at four institutions. Patients who progressed to HGD or EAC in ≥1 year (n = 79) were matched with patients who did not progress (n = 287). Biopsies were assigned randomly to training or validation sets. Immunofluorescence analyses were performed for 14 biomarkers and quantitative biomarker and morphometric features were analyzed. Prognostic features were selected in the training set and combined into classifiers. The top-performing classifier was assessed in the validation set. A 3-tier, 15-feature classifier was selected in the training set and tested in the validation set. The classifier stratified patients into low-, intermediate-, and high-risk classes [HR, 9.42; 95% confidence interval, 4.6-19.24 (high-risk vs. low-risk); P < 0.0001]. It also provided independent prognostic information that outperformed predictions based on pathology analysis, segment length, age, sex, or p53 overexpression. We developed a tissue systems pathology test that better predicts risk of progression in Barrett's esophagus than clinicopathologic variables. The test has the potential to improve upon histologic analysis as an objective method to risk stratify Barrett's esophagus patients. Cancer Epidemiol Biomarkers Prev; 25(6); 958-68. ©2016 AACR. ©2016 American Association for Cancer Research.

AdaBoost-based algorithm for network intrusion detection.

PubMed

Hu, Weiming; Hu, Wei; Maybank, Steve

2008-04-01

Network intrusion detection aims at distinguishing the attacks on the Internet from normal use of the Internet. It is an indispensable part of the information security system. Due to the variety of network behaviors and the rapid development of attack fashions, it is necessary to develop fast machine-learning-based intrusion detection algorithms with high detection rates and low false-alarm rates. In this correspondence, we propose an intrusion detection algorithm based on the AdaBoost algorithm. In the algorithm, decision stumps are used as weak classifiers. The decision rules are provided for both categorical and continuous features. By combining the weak classifiers for continuous features and the weak classifiers for categorical features into a strong classifier, the relations between these two different types of features are handled naturally, without any forced conversions between continuous and categorical features. Adaptable initial weights and a simple strategy for avoiding overfitting are adopted to improve the performance of the algorithm. Experimental results show that our algorithm has low computational complexity and error rates, as compared with algorithms of higher computational complexity, as tested on the benchmark sample data.

Objective Measurement of Erythema in Psoriasis using Digital Color Photography with Color Calibration

PubMed Central

Raina, Abhay; Hennessy, Ricky; Rains, Michael; Allred, James; Hirshburg, Jason M; Diven, Dayna; Markey, Mia K.

2016-01-01

Background Traditional metrics for evaluating the severity of psoriasis are subjective, which complicates efforts to measure effective treatments in clinical trials. Methods We collected images of psoriasis plaques and calibrated the coloration of the images according to an included color card. Features were extracted from the images and used to train a linear discriminant analysis classifier with cross-validation to automatically classify the degree of erythema. The results were tested against numerical scores obtained by a panel of dermatologists using a standard rating system. Results Quantitative measures of erythema based on the digital color images showed good agreement with subjective assessment of erythema severity (κ = 0.4203). The color calibration process improved the agreement from κ = 0.2364 to κ = 0.4203. Conclusions We propose a method for the objective measurement of the psoriasis severity parameter of erythema and show that the calibration process improved the results. PMID:26517973

Object Classification in Semi Structured Enviroment Using Forward-Looking Sonar

PubMed Central

dos Santos, Matheus; Ribeiro, Pedro Otávio; Núñez, Pedro; Botelho, Silvia

2017-01-01

The submarine exploration using robots has been increasing in recent years. The automation of tasks such as monitoring, inspection, and underwater maintenance requires the understanding of the robot’s environment. The object recognition in the scene is becoming a critical issue for these systems. On this work, an underwater object classification pipeline applied in acoustic images acquired by Forward-Looking Sonar (FLS) are studied. The object segmentation combines thresholding, connected pixels searching and peak of intensity analyzing techniques. The object descriptor extract intensity and geometric features of the detected objects. A comparison between the Support Vector Machine, K-Nearest Neighbors, and Random Trees classifiers are presented. An open-source tool was developed to annotate and classify the objects and evaluate their classification performance. The proposed method efficiently segments and classifies the structures in the scene using a real dataset acquired by an underwater vehicle in a harbor area. Experimental results demonstrate the robustness and accuracy of the method described in this paper. PMID:28961163

Prediction of recombinant protein overexpression in Escherichia coli using a machine learning based model (RPOLP).

PubMed

Habibi, Narjeskhatoon; Norouzi, Alireza; Mohd Hashim, Siti Z; Shamsir, Mohd Shahir; Samian, Razip

2015-11-01

Recombinant protein overexpression, an important biotechnological process, is ruled by complex biological rules which are mostly unknown, is in need of an intelligent algorithm so as to avoid resource-intensive lab-based trial and error experiments in order to determine the expression level of the recombinant protein. The purpose of this study is to propose a predictive model to estimate the level of recombinant protein overexpression for the first time in the literature using a machine learning approach based on the sequence, expression vector, and expression host. The expression host was confined to Escherichia coli which is the most popular bacterial host to overexpress recombinant proteins. To provide a handle to the problem, the overexpression level was categorized as low, medium and high. A set of features which were likely to affect the overexpression level was generated based on the known facts (e.g. gene length) and knowledge gathered from related literature. Then, a representative sub-set of features generated in the previous objective was determined using feature selection techniques. Finally a predictive model was developed using random forest classifier which was able to adequately classify the multi-class imbalanced small dataset constructed. The result showed that the predictive model provided a promising accuracy of 80% on average, in estimating the overexpression level of a recombinant protein. Copyright © 2015 Elsevier Ltd. All rights reserved.

Object Detection and Classification by Decision-Level Fusion for Intelligent Vehicle Systems.

PubMed

Oh, Sang-Il; Kang, Hang-Bong

2017-01-22

To understand driving environments effectively, it is important to achieve accurate detection and classification of objects detected by sensor-based intelligent vehicle systems, which are significantly important tasks. Object detection is performed for the localization of objects, whereas object classification recognizes object classes from detected object regions. For accurate object detection and classification, fusing multiple sensor information into a key component of the representation and perception processes is necessary. In this paper, we propose a new object-detection and classification method using decision-level fusion. We fuse the classification outputs from independent unary classifiers, such as 3D point clouds and image data using a convolutional neural network (CNN). The unary classifiers for the two sensors are the CNN with five layers, which use more than two pre-trained convolutional layers to consider local to global features as data representation. To represent data using convolutional layers, we apply region of interest (ROI) pooling to the outputs of each layer on the object candidate regions generated using object proposal generation to realize color flattening and semantic grouping for charge-coupled device and Light Detection And Ranging (LiDAR) sensors. We evaluate our proposed method on a KITTI benchmark dataset to detect and classify three object classes: cars, pedestrians and cyclists. The evaluation results show that the proposed method achieves better performance than the previous methods. Our proposed method extracted approximately 500 proposals on a 1226 × 370 image, whereas the original selective search method extracted approximately 10 6 × n proposals. We obtained classification performance with 77.72% mean average precision over the entirety of the classes in the moderate detection level of the KITTI benchmark dataset.

Object Detection and Classification by Decision-Level Fusion for Intelligent Vehicle Systems

PubMed Central

Oh, Sang-Il; Kang, Hang-Bong

2017-01-01

To understand driving environments effectively, it is important to achieve accurate detection and classification of objects detected by sensor-based intelligent vehicle systems, which are significantly important tasks. Object detection is performed for the localization of objects, whereas object classification recognizes object classes from detected object regions. For accurate object detection and classification, fusing multiple sensor information into a key component of the representation and perception processes is necessary. In this paper, we propose a new object-detection and classification method using decision-level fusion. We fuse the classification outputs from independent unary classifiers, such as 3D point clouds and image data using a convolutional neural network (CNN). The unary classifiers for the two sensors are the CNN with five layers, which use more than two pre-trained convolutional layers to consider local to global features as data representation. To represent data using convolutional layers, we apply region of interest (ROI) pooling to the outputs of each layer on the object candidate regions generated using object proposal generation to realize color flattening and semantic grouping for charge-coupled device and Light Detection And Ranging (LiDAR) sensors. We evaluate our proposed method on a KITTI benchmark dataset to detect and classify three object classes: cars, pedestrians and cyclists. The evaluation results show that the proposed method achieves better performance than the previous methods. Our proposed method extracted approximately 500 proposals on a 1226×370 image, whereas the original selective search method extracted approximately 106×n proposals. We obtained classification performance with 77.72% mean average precision over the entirety of the classes in the moderate detection level of the KITTI benchmark dataset. PMID:28117742

DOE Office of Scientific and Technical Information (OSTI.GOV)

Jing, Yaqi; Meng, Qinghao, E-mail: qh-meng@tju.edu.cn; Qi, Peifeng

An electronic nose (e-nose) was designed to classify Chinese liquors of the same aroma style. A new method of feature reduction which combined feature selection with feature extraction was proposed. Feature selection method used 8 feature-selection algorithms based on information theory and reduced the dimension of the feature space to 41. Kernel entropy component analysis was introduced into the e-nose system as a feature extraction method and the dimension of feature space was reduced to 12. Classification of Chinese liquors was performed by using back propagation artificial neural network (BP-ANN), linear discrimination analysis (LDA), and a multi-linear classifier. The classificationmore » rate of the multi-linear classifier was 97.22%, which was higher than LDA and BP-ANN. Finally the classification of Chinese liquors according to their raw materials and geographical origins was performed using the proposed multi-linear classifier and classification rate was 98.75% and 100%, respectively.« less

A Novel Optical/digital Processing System for Pattern Recognition

NASA Technical Reports Server (NTRS)

Boone, Bradley G.; Shukla, Oodaye B.

1993-01-01

This paper describes two processing algorithms that can be implemented optically: the Radon transform and angular correlation. These two algorithms can be combined in one optical processor to extract all the basic geometric and amplitude features from objects embedded in video imagery. We show that the internal amplitude structure of objects is recovered by the Radon transform, which is a well-known result, but, in addition, we show simulation results that calculate angular correlation, a simple but unique algorithm that extracts object boundaries from suitably threshold images from which length, width, area, aspect ratio, and orientation can be derived. In addition to circumventing scale and rotation distortions, these simulations indicate that the features derived from the angular correlation algorithm are relatively insensitive to tracking shifts and image noise. Some optical architecture concepts, including one based on micro-optical lenslet arrays, have been developed to implement these algorithms. Simulation test and evaluation using simple synthetic object data will be described, including results of a study that uses object boundaries (derivable from angular correlation) to classify simple objects using a neural network.

Genetic algorithm based feature selection combined with dual classification for the automated detection of proliferative diabetic retinopathy.

PubMed

Welikala, R A; Fraz, M M; Dehmeshki, J; Hoppe, A; Tah, V; Mann, S; Williamson, T H; Barman, S A

2015-07-01

Proliferative diabetic retinopathy (PDR) is a condition that carries a high risk of severe visual impairment. The hallmark of PDR is the growth of abnormal new vessels. In this paper, an automated method for the detection of new vessels from retinal images is presented. This method is based on a dual classification approach. Two vessel segmentation approaches are applied to create two separate binary vessel map which each hold vital information. Local morphology features are measured from each binary vessel map to produce two separate 4-D feature vectors. Independent classification is performed for each feature vector using a support vector machine (SVM) classifier. The system then combines these individual outcomes to produce a final decision. This is followed by the creation of additional features to generate 21-D feature vectors, which feed into a genetic algorithm based feature selection approach with the objective of finding feature subsets that improve the performance of the classification. Sensitivity and specificity results using a dataset of 60 images are 0.9138 and 0.9600, respectively, on a per patch basis and 1.000 and 0.975, respectively, on a per image basis. Copyright © 2015 Elsevier Ltd. All rights reserved.

Performance comparison of classifiers for differentiation among obstructive lung diseases based on features of texture analysis at HRCT

NASA Astrophysics Data System (ADS)

Lee, Youngjoo; Seo, Joon Beom; Kang, Bokyoung; Kim, Dongil; Lee, June Goo; Kim, Song Soo; Kim, Namkug; Kang, Suk Ho

2007-03-01

The performance of classification algorithms for differentiating among obstructive lung diseases based on features from texture analysis using HRCT (High Resolution Computerized Tomography) images was compared. HRCT can provide accurate information for the detection of various obstructive lung diseases, including centrilobular emphysema, panlobular emphysema and bronchiolitis obliterans. Features on HRCT images can be subtle, however, particularly in the early stages of disease, and image-based diagnosis is subject to inter-observer variation. To automate the diagnosis and improve the accuracy, we compared three types of automated classification systems, naÃve Bayesian classifier, ANN (Artificial Neural Net) and SVM (Support Vector Machine), based on their ability to differentiate among normal lung and three types of obstructive lung diseases. To assess the performance and cross-validation of these three classifiers, 5 folding methods with 5 randomly chosen groups were used. For a more robust result, each validation was repeated 100 times. SVM showed the best performance, with 86.5% overall sensitivity, significantly different from the other classifiers (one way ANOVA, p<0.01). We address the characteristics of each classifier affecting performance and the issue of which classifier is the most suitable for clinical applications, and propose an appropriate method to choose the best classifier and determine its optimal parameters for optimal disease discrimination. These results can be applied to classifiers for differentiation of other diseases.

Heterogeneity wavelet kinetics from DCE-MRI for classifying gene expression based breast cancer recurrence risk.

PubMed

Mahrooghy, Majid; Ashraf, Ahmed B; Daye, Dania; Mies, Carolyn; Feldman, Michael; Rosen, Mark; Kontos, Despina

2013-01-01

Breast tumors are heterogeneous lesions. Intra-tumor heterogeneity presents a major challenge for cancer diagnosis and treatment. Few studies have worked on capturing tumor heterogeneity from imaging. Most studies to date consider aggregate measures for tumor characterization. In this work we capture tumor heterogeneity by partitioning tumor pixels into subregions and extracting heterogeneity wavelet kinetic (HetWave) features from breast dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) to obtain the spatiotemporal patterns of the wavelet coefficients and contrast agent uptake from each partition. Using a genetic algorithm for feature selection, and a logistic regression classifier with leave one-out cross validation, we tested our proposed HetWave features for the task of classifying breast cancer recurrence risk. The classifier based on our features gave an ROC AUC of 0.78, outperforming previously proposed kinetic, texture, and spatial enhancement variance features which give AUCs of 0.69, 0.64, and 0.65, respectively.

Intelligent Fault Diagnosis of HVCB with Feature Space Optimization-Based Random Forest

PubMed Central

Ma, Suliang; Wu, Jianwen; Wang, Yuhao; Jia, Bowen; Jiang, Yuan

2018-01-01

Mechanical faults of high-voltage circuit breakers (HVCBs) always happen over long-term operation, so extracting the fault features and identifying the fault type have become a key issue for ensuring the security and reliability of power supply. Based on wavelet packet decomposition technology and random forest algorithm, an effective identification system was developed in this paper. First, compared with the incomplete description of Shannon entropy, the wavelet packet time-frequency energy rate (WTFER) was adopted as the input vector for the classifier model in the feature selection procedure. Then, a random forest classifier was used to diagnose the HVCB fault, assess the importance of the feature variable and optimize the feature space. Finally, the approach was verified based on actual HVCB vibration signals by considering six typical fault classes. The comparative experiment results show that the classification accuracy of the proposed method with the origin feature space reached 93.33% and reached up to 95.56% with optimized input feature vector of classifier. This indicates that feature optimization procedure is successful, and the proposed diagnosis algorithm has higher efficiency and robustness than traditional methods. PMID:29659548

RecceMan: an interactive recognition assistance for image-based reconnaissance: synergistic effects of human perception and computational methods for object recognition, identification, and infrastructure analysis

NASA Astrophysics Data System (ADS)

El Bekri, Nadia; Angele, Susanne; Ruckhäberle, Martin; Peinsipp-Byma, Elisabeth; Haelke, Bruno

2015-10-01

This paper introduces an interactive recognition assistance system for imaging reconnaissance. This system supports aerial image analysts on missions during two main tasks: Object recognition and infrastructure analysis. Object recognition concentrates on the classification of one single object. Infrastructure analysis deals with the description of the components of an infrastructure and the recognition of the infrastructure type (e.g. military airfield). Based on satellite or aerial images, aerial image analysts are able to extract single object features and thereby recognize different object types. It is one of the most challenging tasks in the imaging reconnaissance. Currently, there are no high potential ATR (automatic target recognition) applications available, as consequence the human observer cannot be replaced entirely. State-of-the-art ATR applications cannot assume in equal measure human perception and interpretation. Why is this still such a critical issue? First, cluttered and noisy images make it difficult to automatically extract, classify and identify object types. Second, due to the changed warfare and the rise of asymmetric threats it is nearly impossible to create an underlying data set containing all features, objects or infrastructure types. Many other reasons like environmental parameters or aspect angles compound the application of ATR supplementary. Due to the lack of suitable ATR procedures, the human factor is still important and so far irreplaceable. In order to use the potential benefits of the human perception and computational methods in a synergistic way, both are unified in an interactive assistance system. RecceMan® (Reconnaissance Manual) offers two different modes for aerial image analysts on missions: the object recognition mode and the infrastructure analysis mode. The aim of the object recognition mode is to recognize a certain object type based on the object features that originated from the image signatures. The infrastructure analysis mode pursues the goal to analyze the function of the infrastructure. The image analyst extracts visually certain target object signatures, assigns them to corresponding object features and is finally able to recognize the object type. The system offers him the possibility to assign the image signatures to features given by sample images. The underlying data set contains a wide range of objects features and object types for different domains like ships or land vehicles. Each domain has its own feature tree developed by aerial image analyst experts. By selecting the corresponding features, the possible solution set of objects is automatically reduced and matches only the objects that contain the selected features. Moreover, we give an outlook of current research in the field of ground target analysis in which we deal with partly automated methods to extract image signatures and assign them to the corresponding features. This research includes methods for automatically determining the orientation of an object and geometric features like width and length of the object. This step enables to reduce automatically the possible object types offered to the image analyst by the interactive recognition assistance system.

Supervised neural network classification of pre-sliced cooked pork ham images using quaternionic singular values.

PubMed

Valous, Nektarios A; Mendoza, Fernando; Sun, Da-Wen; Allen, Paul

2010-03-01

The quaternionic singular value decomposition is a technique to decompose a quaternion matrix (representation of a colour image) into quaternion singular vector and singular value component matrices exposing useful properties. The objective of this study was to use a small portion of uncorrelated singular values, as robust features for the classification of sliced pork ham images, using a supervised artificial neural network classifier. Images were acquired from four qualities of sliced cooked pork ham typically consumed in Ireland (90 slices per quality), having similar appearances. Mahalanobis distances and Pearson product moment correlations were used for feature selection. Six highly discriminating features were used as input to train the neural network. An adaptive feedforward multilayer perceptron classifier was employed to obtain a suitable mapping from the input dataset. The overall correct classification performance for the training, validation and test set were 90.3%, 94.4%, and 86.1%, respectively. The results confirm that the classification performance was satisfactory. Extracting the most informative features led to the recognition of a set of different but visually quite similar textural patterns based on quaternionic singular values. Copyright 2009 Elsevier Ltd. All rights reserved.

[Identification of special quality eggs with NIR spectroscopy technology based on symbol entropy feature extraction method].

PubMed

Zhao, Yong; Hong, Wen-Xue

2011-11-01

Fast, nondestructive and accurate identification of special quality eggs is an urgent problem. The present paper proposed a new feature extraction method based on symbol entropy to identify near infrared spectroscopy of special quality eggs. The authors selected normal eggs, free range eggs, selenium-enriched eggs and zinc-enriched eggs as research objects and measured the near-infrared diffuse reflectance spectra in the range of 12 000-4 000 cm(-1). Raw spectra were symbolically represented with aggregation approximation algorithm and symbolic entropy was extracted as feature vector. An error-correcting output codes multiclass support vector machine classifier was designed to identify the spectrum. Symbolic entropy feature is robust when parameter changed and the highest recognition rate reaches up to 100%. The results show that the identification method of special quality eggs using near-infrared is feasible and the symbol entropy can be used as a new feature extraction method of near-infrared spectra.

Classification of materials for conducting spheroids based on the first order polarization tensor

NASA Astrophysics Data System (ADS)

Khairuddin, TK Ahmad; Mohamad Yunos, N.; Aziz, ZA; Ahmad, T.; Lionheart, WRB

2017-09-01

Polarization tensor is an old terminology in mathematics and physics with many recent industrial applications including medical imaging, nondestructive testing and metal detection. In these applications, it is theoretically formulated based on the mathematical modelling either in electrics, electromagnetics or both. Generally, polarization tensor represents the perturbation in the electric or electromagnetic fields due to the presence of conducting objects and hence, it also desribes the objects. Understanding the properties of the polarization tensor is necessary and important in order to apply it. Therefore, in this study, when the conducting object is a spheroid, we show that the polarization tensor is positive-definite if and only if the conductivity of the object is greater than one. In contrast, we also prove that the polarization tensor is negative-definite if and only if the conductivity of the object is between zero and one. These features categorize the conductivity of the spheroid based on in its polarization tensor and can then help to classify the material of the spheroid.

Non-target adjacent stimuli classification improves performance of classical ERP-based brain computer interface

NASA Astrophysics Data System (ADS)

Ceballos, G. A.; Hernández, L. F.

2015-04-01

Objective. The classical ERP-based speller, or P300 Speller, is one of the most commonly used paradigms in the field of Brain Computer Interfaces (BCI). Several alterations to the visual stimuli presentation system have been developed to avoid unfavorable effects elicited by adjacent stimuli. However, there has been little, if any, regard to useful information contained in responses to adjacent stimuli about spatial location of target symbols. This paper aims to demonstrate that combining the classification of non-target adjacent stimuli with standard classification (target versus non-target) significantly improves classical ERP-based speller efficiency. Approach. Four SWLDA classifiers were trained and combined with the standard classifier: the lower row, upper row, right column and left column classifiers. This new feature extraction procedure and the classification method were carried out on three open databases: the UAM P300 database (Universidad Autonoma Metropolitana, Mexico), BCI competition II (dataset IIb) and BCI competition III (dataset II). Main results. The inclusion of the classification of non-target adjacent stimuli improves target classification in the classical row/column paradigm. A gain in mean single trial classification of 9.6% and an overall improvement of 25% in simulated spelling speed was achieved. Significance. We have provided further evidence that the ERPs produced by adjacent stimuli present discriminable features, which could provide additional information about the spatial location of intended symbols. This work promotes the searching of information on the peripheral stimulation responses to improve the performance of emerging visual ERP-based spellers.

Applying machine learning classification techniques to automate sky object cataloguing

NASA Astrophysics Data System (ADS)

Fayyad, Usama M.; Doyle, Richard J.; Weir, W. Nick; Djorgovski, Stanislav

1993-08-01

We describe the application of an Artificial Intelligence machine learning techniques to the development of an automated tool for the reduction of a large scientific data set. The 2nd Mt. Palomar Northern Sky Survey is nearly completed. This survey provides comprehensive coverage of the northern celestial hemisphere in the form of photographic plates. The plates are being transformed into digitized images whose quality will probably not be surpassed in the next ten to twenty years. The images are expected to contain on the order of 107 galaxies and 108 stars. Astronomers wish to determine which of these sky objects belong to various classes of galaxies and stars. Unfortunately, the size of this data set precludes analysis in an exclusively manual fashion. Our approach is to develop a software system which integrates the functions of independently developed techniques for image processing and data classification. Digitized sky images are passed through image processing routines to identify sky objects and to extract a set of features for each object. These routines are used to help select a useful set of attributes for classifying sky objects. Then GID3 (Generalized ID3) and O-B Tree, two inductive learning techniques, learns classification decision trees from examples. These classifiers will then be applied to new data. These developmnent process is highly interactive, with astronomer input playing a vital role. Astronomers refine the feature set used to construct sky object descriptions, and evaluate the performance of the automated classification technique on new data. This paper gives an overview of the machine learning techniques with an emphasis on their general applicability, describes the details of our specific application, and reports the initial encouraging results. The results indicate that our machine learning approach is well-suited to the problem. The primary benefit of the approach is increased data reduction throughput. Another benefit is consistency of classification. The classification rules which are the product of the inductive learning techniques will form an objective, examinable basis for classifying sky objects. A final, not to be underestimated benefit is that astronomers will be freed from the tedium of an intensely visual task to pursue more challenging analysis and interpretation problems based on automatically catalogued data.

Vehicle Detection with Occlusion Handling, Tracking, and OC-SVM Classification: A High Performance Vision-Based System

PubMed Central

Velazquez-Pupo, Roxana; Sierra-Romero, Alberto; Torres-Roman, Deni; Shkvarko, Yuriy V.; Romero-Delgado, Misael

2018-01-01

This paper presents a high performance vision-based system with a single static camera for traffic surveillance, for moving vehicle detection with occlusion handling, tracking, counting, and One Class Support Vector Machine (OC-SVM) classification. In this approach, moving objects are first segmented from the background using the adaptive Gaussian Mixture Model (GMM). After that, several geometric features are extracted, such as vehicle area, height, width, centroid, and bounding box. As occlusion is present, an algorithm was implemented to reduce it. The tracking is performed with adaptive Kalman filter. Finally, the selected geometric features: estimated area, height, and width are used by different classifiers in order to sort vehicles into three classes: small, midsize, and large. Extensive experimental results in eight real traffic videos with more than 4000 ground truth vehicles have shown that the improved system can run in real time under an occlusion index of 0.312 and classify vehicles with a global detection rate or recall, precision, and F-measure of up to 98.190%, and an F-measure of up to 99.051% for midsize vehicles. PMID:29382078

Automatic Detection of Whole Night Snoring Events Using Non-Contact Microphone

PubMed Central

Dafna, Eliran; Tarasiuk, Ariel; Zigel, Yaniv

2013-01-01

Objective Although awareness of sleep disorders is increasing, limited information is available on whole night detection of snoring. Our study aimed to develop and validate a robust, high performance, and sensitive whole-night snore detector based on non-contact technology. Design Sounds during polysomnography (PSG) were recorded using a directional condenser microphone placed 1 m above the bed. An AdaBoost classifier was trained and validated on manually labeled snoring and non-snoring acoustic events. Patients Sixty-seven subjects (age 52.5±13.5 years, BMI 30.8±4.7 kg/m2, m/f 40/27) referred for PSG for obstructive sleep apnea diagnoses were prospectively and consecutively recruited. Twenty-five subjects were used for the design study; the validation study was blindly performed on the remaining forty-two subjects. Measurements and Results To train the proposed sound detector, >76,600 acoustic episodes collected in the design study were manually classified by three scorers into snore and non-snore episodes (e.g., bedding noise, coughing, environmental). A feature selection process was applied to select the most discriminative features extracted from time and spectral domains. The average snore/non-snore detection rate (accuracy) for the design group was 98.4% based on a ten-fold cross-validation technique. When tested on the validation group, the average detection rate was 98.2% with sensitivity of 98.0% (snore as a snore) and specificity of 98.3% (noise as noise). Conclusions Audio-based features extracted from time and spectral domains can accurately discriminate between snore and non-snore acoustic events. This audio analysis approach enables detection and analysis of snoring sounds from a full night in order to produce quantified measures for objective follow-up of patients. PMID:24391903

Material classification and automatic content enrichment of images using supervised learning and knowledge bases

NASA Astrophysics Data System (ADS)

Mallepudi, Sri Abhishikth; Calix, Ricardo A.; Knapp, Gerald M.

2011-02-01

In recent years there has been a rapid increase in the size of video and image databases. Effective searching and retrieving of images from these databases is a significant current research area. In particular, there is a growing interest in query capabilities based on semantic image features such as objects, locations, and materials, known as content-based image retrieval. This study investigated mechanisms for identifying materials present in an image. These capabilities provide additional information impacting conditional probabilities about images (e.g. objects made of steel are more likely to be buildings). These capabilities are useful in Building Information Modeling (BIM) and in automatic enrichment of images. I2T methodologies are a way to enrich an image by generating text descriptions based on image analysis. In this work, a learning model is trained to detect certain materials in images. To train the model, an image dataset was constructed containing single material images of bricks, cloth, grass, sand, stones, and wood. For generalization purposes, an additional set of 50 images containing multiple materials (some not used in training) was constructed. Two different supervised learning classification models were investigated: a single multi-class SVM classifier, and multiple binary SVM classifiers (one per material). Image features included Gabor filter parameters for texture, and color histogram data for RGB components. All classification accuracy scores using the SVM-based method were above 85%. The second model helped in gathering more information from the images since it assigned multiple classes to the images. A framework for the I2T methodology is presented.

[Road Extraction in Remote Sensing Images Based on Spectral and Edge Analysis].

PubMed

Zhao, Wen-zhi; Luo, Li-qun; Guo, Zhou; Yue, Jun; Yu, Xue-ying; Liu, Hui; Wei, Jing

2015-10-01

Roads are typically man-made objects in urban areas. Road extraction from high-resolution images has important applications for urban planning and transportation development. However, due to the confusion of spectral characteristic, it is difficult to distinguish roads from other objects by merely using traditional classification methods that mainly depend on spectral information. Edge is an important feature for the identification of linear objects (e. g. , roads). The distribution patterns of edges vary greatly among different objects. It is crucial to merge edge statistical information into spectral ones. In this study, a new method that combines spectral information and edge statistical features has been proposed. First, edge detection is conducted by using self-adaptive mean-shift algorithm on the panchromatic band, which can greatly reduce pseudo-edges and noise effects. Then, edge statistical features are obtained from the edge statistical model, which measures the length and angle distribution of edges. Finally, by integrating the spectral and edge statistical features, SVM algorithm is used to classify the image and roads are ultimately extracted. A series of experiments are conducted and the results show that the overall accuracy of proposed method is 93% comparing with only 78% overall accuracy of the traditional. The results demonstrate that the proposed method is efficient and valuable for road extraction, especially on high-resolution images.

Coregistered FDG PET/CT-based textural characterization of head and neck cancer for radiation treatment planning.

PubMed

Yu, Huan; Caldwell, Curtis; Mah, Katherine; Mozeg, Daniel

2009-03-01

Coregistered fluoro-deoxy-glucose (FDG) positron emission tomography/computed tomography (PET/CT) has shown potential to improve the accuracy of radiation targeting of head and neck cancer (HNC) when compared to the use of CT simulation alone. The objective of this study was to identify textural features useful in distinguishing tumor from normal tissue in head and neck via quantitative texture analysis of coregistered 18F-FDG PET and CT images. Abnormal and typical normal tissues were manually segmented from PET/CT images of 20 patients with HNC and 20 patients with lung cancer. Texture features including some derived from spatial grey-level dependence matrices (SGLDM) and neighborhood gray-tone-difference matrices (NGTDM) were selected for characterization of these segmented regions of interest (ROIs). Both K nearest neighbors (KNNs) and decision tree (DT)-based KNN classifiers were employed to discriminate images of abnormal and normal tissues. The area under the curve (AZ) of receiver operating characteristics (ROC) was used to evaluate the discrimination performance of features in comparison to an expert observer. The leave-one-out and bootstrap techniques were used to validate the results. The AZ of DT-based KNN classifier was 0.95. Sensitivity and specificity for normal and abnormal tissue classification were 89% and 99%, respectively. In summary, NGTDM features such as PET Coarseness, PET Contrast, and CT Coarseness extracted from FDG PET/CT images provided good discrimination performance. The clinical use of such features may lead to improvement in the accuracy of radiation targeting of HNC.

SVM feature selection based rotation forest ensemble classifiers to improve computer-aided diagnosis of Parkinson disease.

PubMed

Ozcift, Akin

2012-08-01

Parkinson disease (PD) is an age-related deterioration of certain nerve systems, which affects movement, balance, and muscle control of clients. PD is one of the common diseases which affect 1% of people older than 60 years. A new classification scheme based on support vector machine (SVM) selected features to train rotation forest (RF) ensemble classifiers is presented for improving diagnosis of PD. The dataset contains records of voice measurements from 31 people, 23 with PD and each record in the dataset is defined with 22 features. The diagnosis model first makes use of a linear SVM to select ten most relevant features from 22. As a second step of the classification model, six different classifiers are trained with the subset of features. Subsequently, at the third step, the accuracies of classifiers are improved by the utilization of RF ensemble classification strategy. The results of the experiments are evaluated using three metrics; classification accuracy (ACC), Kappa Error (KE) and Area under the Receiver Operating Characteristic (ROC) Curve (AUC). Performance measures of two base classifiers, i.e. KStar and IBk, demonstrated an apparent increase in PD diagnosis accuracy compared to similar studies in literature. After all, application of RF ensemble classification scheme improved PD diagnosis in 5 of 6 classifiers significantly. We, numerically, obtained about 97% accuracy in RF ensemble of IBk (a K-Nearest Neighbor variant) algorithm, which is a quite high performance for Parkinson disease diagnosis.

Max-AUC Feature Selection in Computer-Aided Detection of Polyps in CT Colonography

PubMed Central

Xu, Jian-Wu; Suzuki, Kenji

2014-01-01

We propose a feature selection method based on a sequential forward floating selection (SFFS) procedure to improve the performance of a classifier in computerized detection of polyps in CT colonography (CTC). The feature selection method is coupled with a nonlinear support vector machine (SVM) classifier. Unlike the conventional linear method based on Wilks' lambda, the proposed method selected the most relevant features that would maximize the area under the receiver operating characteristic curve (AUC), which directly maximizes classification performance, evaluated based on AUC value, in the computer-aided detection (CADe) scheme. We presented two variants of the proposed method with different stopping criteria used in the SFFS procedure. The first variant searched all feature combinations allowed in the SFFS procedure and selected the subsets that maximize the AUC values. The second variant performed a statistical test at each step during the SFFS procedure, and it was terminated if the increase in the AUC value was not statistically significant. The advantage of the second variant is its lower computational cost. To test the performance of the proposed method, we compared it against the popular stepwise feature selection method based on Wilks' lambda for a colonic-polyp database (25 polyps and 2624 nonpolyps). We extracted 75 morphologic, gray-level-based, and texture features from the segmented lesion candidate regions. The two variants of the proposed feature selection method chose 29 and 7 features, respectively. Two SVM classifiers trained with these selected features yielded a 96% by-polyp sensitivity at false-positive (FP) rates of 4.1 and 6.5 per patient, respectively. Experiments showed a significant improvement in the performance of the classifier with the proposed feature selection method over that with the popular stepwise feature selection based on Wilks' lambda that yielded 18.0 FPs per patient at the same sensitivity level. PMID:24608058

Max-AUC feature selection in computer-aided detection of polyps in CT colonography.

PubMed

Xu, Jian-Wu; Suzuki, Kenji

2014-03-01

We propose a feature selection method based on a sequential forward floating selection (SFFS) procedure to improve the performance of a classifier in computerized detection of polyps in CT colonography (CTC). The feature selection method is coupled with a nonlinear support vector machine (SVM) classifier. Unlike the conventional linear method based on Wilks' lambda, the proposed method selected the most relevant features that would maximize the area under the receiver operating characteristic curve (AUC), which directly maximizes classification performance, evaluated based on AUC value, in the computer-aided detection (CADe) scheme. We presented two variants of the proposed method with different stopping criteria used in the SFFS procedure. The first variant searched all feature combinations allowed in the SFFS procedure and selected the subsets that maximize the AUC values. The second variant performed a statistical test at each step during the SFFS procedure, and it was terminated if the increase in the AUC value was not statistically significant. The advantage of the second variant is its lower computational cost. To test the performance of the proposed method, we compared it against the popular stepwise feature selection method based on Wilks' lambda for a colonic-polyp database (25 polyps and 2624 nonpolyps). We extracted 75 morphologic, gray-level-based, and texture features from the segmented lesion candidate regions. The two variants of the proposed feature selection method chose 29 and 7 features, respectively. Two SVM classifiers trained with these selected features yielded a 96% by-polyp sensitivity at false-positive (FP) rates of 4.1 and 6.5 per patient, respectively. Experiments showed a significant improvement in the performance of the classifier with the proposed feature selection method over that with the popular stepwise feature selection based on Wilks' lambda that yielded 18.0 FPs per patient at the same sensitivity level.

Automatic extraction of relations between medical concepts in clinical texts

PubMed Central

Harabagiu, Sanda; Roberts, Kirk

2011-01-01

Objective A supervised machine learning approach to discover relations between medical problems, treatments, and tests mentioned in electronic medical records. Materials and methods A single support vector machine classifier was used to identify relations between concepts and to assign their semantic type. Several resources such as Wikipedia, WordNet, General Inquirer, and a relation similarity metric inform the classifier. Results The techniques reported in this paper were evaluated in the 2010 i2b2 Challenge and obtained the highest F1 score for the relation extraction task. When gold standard data for concepts and assertions were available, F1 was 73.7, precision was 72.0, and recall was 75.3. F1 is defined as 2*Precision*Recall/(Precision+Recall). Alternatively, when concepts and assertions were discovered automatically, F1 was 48.4, precision was 57.6, and recall was 41.7. Discussion Although a rich set of features was developed for the classifiers presented in this paper, little knowledge mining was performed from medical ontologies such as those found in UMLS. Future studies should incorporate features extracted from such knowledge sources, which we expect to further improve the results. Moreover, each relation discovery was treated independently. Joint classification of relations may further improve the quality of results. Also, joint learning of the discovery of concepts, assertions, and relations may also improve the results of automatic relation extraction. Conclusion Lexical and contextual features proved to be very important in relation extraction from medical texts. When they are not available to the classifier, the F1 score decreases by 3.7%. In addition, features based on similarity contribute to a decrease of 1.1% when they are not available. PMID:21846787

Classifying smoking urges via machine learning

PubMed Central

Dumortier, Antoine; Beckjord, Ellen; Shiffman, Saul; Sejdić, Ervin

2016-01-01

Background and objective Smoking is the largest preventable cause of death and diseases in the developed world, and advances in modern electronics and machine learning can help us deliver real-time intervention to smokers in novel ways. In this paper, we examine different machine learning approaches to use situational features associated with having or not having urges to smoke during a quit attempt in order to accurately classify high-urge states. Methods To test our machine learning approaches, specifically, Bayes, discriminant analysis and decision tree learning methods, we used a dataset collected from over 300 participants who had initiated a quit attempt. The three classification approaches are evaluated observing sensitivity, specificity, accuracy and precision. Results The outcome of the analysis showed that algorithms based on feature selection make it possible to obtain high classification rates with only a few features selected from the entire dataset. The classification tree method outperformed the naive Bayes and discriminant analysis methods, with an accuracy of the classifications up to 86%. These numbers suggest that machine learning may be a suitable approach to deal with smoking cessation matters, and to predict smoking urges, outlining a potential use for mobile health applications. Conclusions In conclusion, machine learning classifiers can help identify smoking situations, and the search for the best features and classifier parameters significantly improves the algorithms’ performance. In addition, this study also supports the usefulness of new technologies in improving the effect of smoking cessation interventions, the management of time and patients by therapists, and thus the optimization of available health care resources. Future studies should focus on providing more adaptive and personalized support to people who really need it, in a minimum amount of time by developing novel expert systems capable of delivering real-time interventions. PMID:28110725

a Point Cloud Classification Approach Based on Vertical Structures of Ground Objects

NASA Astrophysics Data System (ADS)

Zhao, Y.; Hu, Q.; Hu, W.

2018-04-01

This paper proposes a novel method for point cloud classification using vertical structural characteristics of ground objects. Since urbanization develops rapidly nowadays, urban ground objects also change frequently. Conventional photogrammetric methods cannot satisfy the requirements of updating the ground objects' information efficiently, so LiDAR (Light Detection and Ranging) technology is employed to accomplish this task. LiDAR data, namely point cloud data, can obtain detailed three-dimensional coordinates of ground objects, but this kind of data is discrete and unorganized. To accomplish ground objects classification with point cloud, we first construct horizontal grids and vertical layers to organize point cloud data, and then calculate vertical characteristics, including density and measures of dispersion, and form characteristic curves for each grids. With the help of PCA processing and K-means algorithm, we analyze the similarities and differences of characteristic curves. Curves that have similar features will be classified into the same class and point cloud correspond to these curves will be classified as well. The whole process is simple but effective, and this approach does not need assistance of other data sources. In this study, point cloud data are classified into three classes, which are vegetation, buildings, and roads. When horizontal grid spacing and vertical layer spacing are 3 m and 1 m respectively, vertical characteristic is set as density, and the number of dimensions after PCA processing is 11, the overall precision of classification result is about 86.31 %. The result can help us quickly understand the distribution of various ground objects.

Building an automated SOAP classifier for emergency department reports.

PubMed

Mowery, Danielle; Wiebe, Janyce; Visweswaran, Shyam; Harkema, Henk; Chapman, Wendy W

2012-02-01

Information extraction applications that extract structured event and entity information from unstructured text can leverage knowledge of clinical report structure to improve performance. The Subjective, Objective, Assessment, Plan (SOAP) framework, used to structure progress notes to facilitate problem-specific, clinical decision making by physicians, is one example of a well-known, canonical structure in the medical domain. Although its applicability to structuring data is understood, its contribution to information extraction tasks has not yet been determined. The first step to evaluating the SOAP framework's usefulness for clinical information extraction is to apply the model to clinical narratives and develop an automated SOAP classifier that classifies sentences from clinical reports. In this quantitative study, we applied the SOAP framework to sentences from emergency department reports, and trained and evaluated SOAP classifiers built with various linguistic features. We found the SOAP framework can be applied manually to emergency department reports with high agreement (Cohen's kappa coefficients over 0.70). Using a variety of features, we found classifiers for each SOAP class can be created with moderate to outstanding performance with F(1) scores of 93.9 (subjective), 94.5 (objective), 75.7 (assessment), and 77.0 (plan). We look forward to expanding the framework and applying the SOAP classification to clinical information extraction tasks. Copyright © 2011. Published by Elsevier Inc.

Classification of subsurface objects using singular values derived from signal frames

DOEpatents

Chambers, David H; Paglieroni, David W

2014-05-06

The classification system represents a detected object with a feature vector derived from the return signals acquired by an array of N transceivers operating in multistatic mode. The classification system generates the feature vector by transforming the real-valued return signals into complex-valued spectra, using, for example, a Fast Fourier Transform. The classification system then generates a feature vector of singular values for each user-designated spectral sub-band by applying a singular value decomposition (SVD) to the N.times.N square complex-valued matrix formed from sub-band samples associated with all possible transmitter-receiver pairs. The resulting feature vector of singular values may be transformed into a feature vector of singular value likelihoods and then subjected to a multi-category linear or neural network classifier for object classification.

Automated discrimination of dicentric and monocentric chromosomes by machine learning-based image processing.

PubMed

Li, Yanxin; Knoll, Joan H; Wilkins, Ruth C; Flegal, Farrah N; Rogan, Peter K

2016-05-01

Dose from radiation exposure can be estimated from dicentric chromosome (DC) frequencies in metaphase cells of peripheral blood lymphocytes. We automated DC detection by extracting features in Giemsa-stained metaphase chromosome images and classifying objects by machine learning (ML). DC detection involves (i) intensity thresholded segmentation of metaphase objects, (ii) chromosome separation by watershed transformation and elimination of inseparable chromosome clusters, fragments and staining debris using a morphological decision tree filter, (iii) determination of chromosome width and centreline, (iv) derivation of centromere candidates, and (v) distinction of DCs from monocentric chromosomes (MC) by ML. Centromere candidates are inferred from 14 image features input to a Support Vector Machine (SVM). Sixteen features derived from these candidates are then supplied to a Boosting classifier and a second SVM which determines whether a chromosome is either a DC or MC. The SVM was trained with 292 DCs and 3135 MCs, and then tested with cells exposed to either low (1 Gy) or high (2-4 Gy) radiation dose. Results were then compared with those of 3 experts. True positive rates (TPR) and positive predictive values (PPV) were determined for the tuning parameter, σ. At larger σ, PPV decreases and TPR increases. At high dose, for σ = 1.3, TPR = 0.52 and PPV = 0.83, while at σ = 1.6, the TPR = 0.65 and PPV = 0.72. At low dose and σ = 1.3, TPR = 0.67 and PPV = 0.26. The algorithm differentiates DCs from MCs, overlapped chromosomes and other objects with acceptable accuracy over a wide range of radiation exposures. © 2016 Wiley Periodicals, Inc.

DOE Office of Scientific and Technical Information (OSTI.GOV)

Eads, Damian Ryan; Rosten, Edward; Helmbold, David

The authors present BEAMER: a new spatially exploitative approach to learning object detectors which shows excellent results when applied to the task of detecting objects in greyscale aerial imagery in the presence of ambiguous and noisy data. There are four main contributions used to produce these results. First, they introduce a grammar-guided feature extraction system, enabling the exploration of a richer feature space while constraining the features to a useful subset. This is specified with a rule-based generative grammer crafted by a human expert. Second, they learn a classifier on this data using a newly proposed variant of AdaBoost whichmore » takes into account the spatially correlated nature of the data. Third, they perform another round of training to optimize the method of converting the pixel classifications generated by boosting into a high quality set of (x,y) locations. lastly, they carefully define three common problems in object detection and define two evaluation criteria that are tightly matched to these problems. Major strengths of this approach are: (1) a way of randomly searching a broad feature space, (2) its performance when evaluated on well-matched evaluation criteria, and (3) its use of the location prediction domain to learn object detectors as well as to generate detections that perform well on several tasks: object counting, tracking, and target detection. They demonstrate the efficacy of BEAMER with a comprehensive experimental evaluation on a challenging data set.« less

Adaptive Morphological Feature-Based Object Classifier for a Color Imaging System

NASA Technical Reports Server (NTRS)

McDowell, Mark; Gray, Elizabeth

2009-01-01

Utilizing a Compact Color Microscope Imaging System (CCMIS), a unique algorithm has been developed that combines human intelligence along with machine vision techniques to produce an autonomous microscope tool for biomedical, industrial, and space applications. This technique is based on an adaptive, morphological, feature-based mapping function comprising 24 mutually inclusive feature metrics that are used to determine the metrics for complex cell/objects derived from color image analysis. Some of the features include: Area (total numbers of non-background pixels inside and including the perimeter), Bounding Box (smallest rectangle that bounds and object), centerX (x-coordinate of intensity-weighted, center-of-mass of an entire object or multi-object blob), centerY (y-coordinate of intensity-weighted, center-of-mass, of an entire object or multi-object blob), Circumference (a measure of circumference that takes into account whether neighboring pixels are diagonal, which is a longer distance than horizontally or vertically joined pixels), . Elongation (measure of particle elongation given as a number between 0 and 1. If equal to 1, the particle bounding box is square. As the elongation decreases from 1, the particle becomes more elongated), . Ext_vector (extremal vector), . Major Axis (the length of a major axis of a smallest ellipse encompassing an object), . Minor Axis (the length of a minor axis of a smallest ellipse encompassing an object), . Partial (indicates if the particle extends beyond the field of view), . Perimeter Points (points that make up a particle perimeter), . Roundness [(4(pi) x area)/perimeter(squared)) the result is a measure of object roundness, or compactness, given as a value between 0 and 1. The greater the ratio, the rounder the object.], . Thin in center (determines if an object becomes thin in the center, (figure-eight-shaped), . Theta (orientation of the major axis), . Smoothness and color metrics for each component (red, green, blue) the minimum, maximum, average, and standard deviation within the particle are tracked. These metrics can be used for autonomous analysis of color images from a microscope, video camera, or digital, still image. It can also automatically identify tumor morphology of stained images and has been used to detect stained cell phenomena (see figure).

Computer Vision and Machine Learning for Autonomous Characterization of AM Powder Feedstocks

NASA Astrophysics Data System (ADS)

DeCost, Brian L.; Jain, Harshvardhan; Rollett, Anthony D.; Holm, Elizabeth A.

2017-03-01

By applying computer vision and machine learning methods, we develop a system to characterize powder feedstock materials for metal additive manufacturing (AM). Feature detection and description algorithms are applied to create a microstructural scale image representation that can be used to cluster, compare, and analyze powder micrographs. When applied to eight commercial feedstock powders, the system classifies powder images into the correct material systems with greater than 95% accuracy. The system also identifies both representative and atypical powder images. These results suggest the possibility of measuring variations in powders as a function of processing history, relating microstructural features of powders to properties relevant to their performance in AM processes, and defining objective material standards based on visual images. A significant advantage of the computer vision approach is that it is autonomous, objective, and repeatable.

A liver cirrhosis classification on B-mode ultrasound images by the use of higher order local autocorrelation features

NASA Astrophysics Data System (ADS)

Sasaki, Kenya; Mitani, Yoshihiro; Fujita, Yusuke; Hamamoto, Yoshihiko; Sakaida, Isao

2017-02-01

In this paper, in order to classify liver cirrhosis on regions of interest (ROIs) images from B-mode ultrasound images, we have proposed to use the higher order local autocorrelation (HLAC) features. In a previous study, we tried to classify liver cirrhosis by using a Gabor filter based approach. However, the classification performance of the Gabor feature was poor from our preliminary experimental results. In order accurately to classify liver cirrhosis, we examined to use the HLAC features for liver cirrhosis classification. The experimental results show the effectiveness of HLAC features compared with the Gabor feature. Furthermore, by using a binary image made by an adaptive thresholding method, the classification performance of HLAC features has improved.

Efficient and sparse feature selection for biomedical text classification via the elastic net: Application to ICU risk stratification from nursing notes.

PubMed

Marafino, Ben J; Boscardin, W John; Dudley, R Adams

2015-04-01

Sparsity is often a desirable property of statistical models, and various feature selection methods exist so as to yield sparser and interpretable models. However, their application to biomedical text classification, particularly to mortality risk stratification among intensive care unit (ICU) patients, has not been thoroughly studied. To develop and characterize sparse classifiers based on the free text of nursing notes in order to predict ICU mortality risk and to discover text features most strongly associated with mortality. We selected nursing notes from the first 24h of ICU admission for 25,826 adult ICU patients from the MIMIC-II database. We then developed a pair of stochastic gradient descent-based classifiers with elastic-net regularization. We also studied the performance-sparsity tradeoffs of both classifiers as their regularization parameters were varied. The best-performing classifier achieved a 10-fold cross-validated AUC of 0.897 under the log loss function and full L2 regularization, while full L1 regularization used just 0.00025% of candidate input features and resulted in an AUC of 0.889. Using the log loss (range of AUCs 0.889-0.897) yielded better performance compared to the hinge loss (0.850-0.876), but the latter yielded even sparser models. Most features selected by both classifiers appear clinically relevant and correspond to predictors already present in existing ICU mortality models. The sparser classifiers were also able to discover a number of informative - albeit nonclinical - features. The elastic-net-regularized classifiers perform reasonably well and are capable of reducing the number of features required by over a thousandfold, with only a modest impact on performance. Copyright © 2015 Elsevier Inc. All rights reserved.

Integrating machine learning techniques and high-resolution imagery to generate GIS-ready information for urban water consumption studies

NASA Astrophysics Data System (ADS)

Wolf, Nils; Hof, Angela

2012-10-01

Urban sprawl driven by shifts in tourism development produces new suburban landscapes of water consumption on Mediterranean coasts. Golf courses, ornamental, 'Atlantic' gardens and swimming pools are the most striking artefacts of this transformation, threatening the local water supply systems and exacerbating water scarcity. In the face of climate change, urban landscape irrigation is becoming increasingly important from a resource management point of view. This paper adopts urban remote sensing towards a targeted mapping approach using machine learning techniques and highresolution satellite imagery (WorldView-2) to generate GIS-ready information for urban water consumption studies. Swimming pools, vegetation and - as a subgroup of vegetation - turf grass are extracted as important determinants of water consumption. For image analysis, the complex nature of urban environments suggests spatial-spectral classification, i.e. the complementary use of the spectral signature and spatial descriptors. Multiscale image segmentation provides means to extract the spatial descriptors - namely object feature layers - which can be concatenated at pixel level to the spectral signature. This study assesses the value of object features using different machine learning techniques and amounts of labeled information for learning. The results indicate the benefit of the spatial-spectral approach if combined with appropriate classifiers like tree-based ensembles or support vector machines, which can handle high dimensionality. Finally, a Random Forest classifier was chosen to deliver the classified input data for the estimation of evaporative water loss and net landscape irrigation requirements.

Automated Recognition of 3D Features in GPIR Images

NASA Technical Reports Server (NTRS)

Park, Han; Stough, Timothy; Fijany, Amir

2007-01-01

A method of automated recognition of three-dimensional (3D) features in images generated by ground-penetrating imaging radar (GPIR) is undergoing development. GPIR 3D images can be analyzed to detect and identify such subsurface features as pipes and other utility conduits. Until now, much of the analysis of GPIR images has been performed manually by expert operators who must visually identify and track each feature. The present method is intended to satisfy a need for more efficient and accurate analysis by means of algorithms that can automatically identify and track subsurface features, with minimal supervision by human operators. In this method, data from multiple sources (for example, data on different features extracted by different algorithms) are fused together for identifying subsurface objects. The algorithms of this method can be classified in several different ways. In one classification, the algorithms fall into three classes: (1) image-processing algorithms, (2) feature- extraction algorithms, and (3) a multiaxis data-fusion/pattern-recognition algorithm that includes a combination of machine-learning, pattern-recognition, and object-linking algorithms. The image-processing class includes preprocessing algorithms for reducing noise and enhancing target features for pattern recognition. The feature-extraction algorithms operate on preprocessed data to extract such specific features in images as two-dimensional (2D) slices of a pipe. Then the multiaxis data-fusion/ pattern-recognition algorithm identifies, classifies, and reconstructs 3D objects from the extracted features. In this process, multiple 2D features extracted by use of different algorithms and representing views along different directions are used to identify and reconstruct 3D objects. In object linking, which is an essential part of this process, features identified in successive 2D slices and located within a threshold radius of identical features in adjacent slices are linked in a directed-graph data structure. Relative to past approaches, this multiaxis approach offers the advantages of more reliable detections, better discrimination of objects, and provision of redundant information, which can be helpful in filling gaps in feature recognition by one of the component algorithms. The image-processing class also includes postprocessing algorithms that enhance identified features to prepare them for further scrutiny by human analysts (see figure). Enhancement of images as a postprocessing step is a significant departure from traditional practice, in which enhancement of images is a preprocessing step.

Training Classifiers with Shadow Features for Sensor-Based Human Activity Recognition.

PubMed

Fong, Simon; Song, Wei; Cho, Kyungeun; Wong, Raymond; Wong, Kelvin K L

2017-02-27

In this paper, a novel training/testing process for building/using a classification model based on human activity recognition (HAR) is proposed. Traditionally, HAR has been accomplished by a classifier that learns the activities of a person by training with skeletal data obtained from a motion sensor, such as Microsoft Kinect. These skeletal data are the spatial coordinates (x, y, z) of different parts of the human body. The numeric information forms time series, temporal records of movement sequences that can be used for training a classifier. In addition to the spatial features that describe current positions in the skeletal data, new features called 'shadow features' are used to improve the supervised learning efficacy of the classifier. Shadow features are inferred from the dynamics of body movements, and thereby modelling the underlying momentum of the performed activities. They provide extra dimensions of information for characterising activities in the classification process, and thereby significantly improve the classification accuracy. Two cases of HAR are tested using a classification model trained with shadow features: one is by using wearable sensor and the other is by a Kinect-based remote sensor. Our experiments can demonstrate the advantages of the new method, which will have an impact on human activity detection research.

On the use of feature selection to improve the detection of sea oil spills in SAR images

NASA Astrophysics Data System (ADS)

Mera, David; Bolon-Canedo, Veronica; Cotos, J. M.; Alonso-Betanzos, Amparo

2017-03-01

Fast and effective oil spill detection systems are crucial to ensure a proper response to environmental emergencies caused by hydrocarbon pollution on the ocean's surface. Typically, these systems uncover not only oil spills, but also a high number of look-alikes. The feature extraction is a critical and computationally intensive phase where each detected dark spot is independently examined. Traditionally, detection systems use an arbitrary set of features to discriminate between oil spills and look-alikes phenomena. However, Feature Selection (FS) methods based on Machine Learning (ML) have proved to be very useful in real domains for enhancing the generalization capabilities of the classifiers, while discarding the existing irrelevant features. In this work, we present a generic and systematic approach, based on FS methods, for choosing a concise and relevant set of features to improve the oil spill detection systems. We have compared five FS methods: Correlation-based feature selection (CFS), Consistency-based filter, Information Gain, ReliefF and Recursive Feature Elimination for Support Vector Machine (SVM-RFE). They were applied on a 141-input vector composed of features from a collection of outstanding studies. Selected features were validated via a Support Vector Machine (SVM) classifier and the results were compared with previous works. Test experiments revealed that the classifier trained with the 6-input feature vector proposed by SVM-RFE achieved the best accuracy and Cohen's kappa coefficient (87.1% and 74.06% respectively). This is a smaller feature combination with similar or even better classification accuracy than previous works. The presented finding allows to speed up the feature extraction phase without reducing the classifier accuracy. Experiments also confirmed the significance of the geometrical features since 75.0% of the different features selected by the applied FS methods as well as 66.67% of the proposed 6-input feature vector belong to this category.

Neonatal Seizure Detection Using Deep Convolutional Neural Networks.

PubMed

Ansari, Amir H; Cherian, Perumpillichira J; Caicedo, Alexander; Naulaers, Gunnar; De Vos, Maarten; Van Huffel, Sabine

2018-04-02

Identifying a core set of features is one of the most important steps in the development of an automated seizure detector. In most of the published studies describing features and seizure classifiers, the features were hand-engineered, which may not be optimal. The main goal of the present paper is using deep convolutional neural networks (CNNs) and random forest to automatically optimize feature selection and classification. The input of the proposed classifier is raw multi-channel EEG and the output is the class label: seizure/nonseizure. By training this network, the required features are optimized, while fitting a nonlinear classifier on the features. After training the network with EEG recordings of 26 neonates, five end layers performing the classification were replaced with a random forest classifier in order to improve the performance. This resulted in a false alarm rate of 0.9 per hour and seizure detection rate of 77% using a test set of EEG recordings of 22 neonates that also included dubious seizures. The newly proposed CNN classifier outperformed three data-driven feature-based approaches and performed similar to a previously developed heuristic method.

Comparison of Different EHG Feature Selection Methods for the Detection of Preterm Labor

PubMed Central

Alamedine, D.; Khalil, M.; Marque, C.

2013-01-01

Numerous types of linear and nonlinear features have been extracted from the electrohysterogram (EHG) in order to classify labor and pregnancy contractions. As a result, the number of available features is now very large. The goal of this study is to reduce the number of features by selecting only the relevant ones which are useful for solving the classification problem. This paper presents three methods for feature subset selection that can be applied to choose the best subsets for classifying labor and pregnancy contractions: an algorithm using the Jeffrey divergence (JD) distance, a sequential forward selection (SFS) algorithm, and a binary particle swarm optimization (BPSO) algorithm. The two last methods are based on a classifier and were tested with three types of classifiers. These methods have allowed us to identify common features which are relevant for contraction classification. PMID:24454536

Applying data fusion techniques for benthic habitat mapping and monitoring in a coral reef ecosystem

NASA Astrophysics Data System (ADS)

Zhang, Caiyun

2015-06-01

Accurate mapping and effective monitoring of benthic habitat in the Florida Keys are critical in developing management strategies for this valuable coral reef ecosystem. For this study, a framework was designed for automated benthic habitat mapping by combining multiple data sources (hyperspectral, aerial photography, and bathymetry data) and four contemporary imagery processing techniques (data fusion, Object-based Image Analysis (OBIA), machine learning, and ensemble analysis). In the framework, 1-m digital aerial photograph was first merged with 17-m hyperspectral imagery and 10-m bathymetry data using a pixel/feature-level fusion strategy. The fused dataset was then preclassified by three machine learning algorithms (Random Forest, Support Vector Machines, and k-Nearest Neighbor). Final object-based habitat maps were produced through ensemble analysis of outcomes from three classifiers. The framework was tested for classifying a group-level (3-class) and code-level (9-class) habitats in a portion of the Florida Keys. Informative and accurate habitat maps were achieved with an overall accuracy of 88.5% and 83.5% for the group-level and code-level classifications, respectively.

Automatic identification of high impact articles in PubMed to support clinical decision making.

PubMed

Bian, Jiantao; Morid, Mohammad Amin; Jonnalagadda, Siddhartha; Luo, Gang; Del Fiol, Guilherme

2017-09-01

The practice of evidence-based medicine involves integrating the latest best available evidence into patient care decisions. Yet, critical barriers exist for clinicians' retrieval of evidence that is relevant for a particular patient from primary sources such as randomized controlled trials and meta-analyses. To help address those barriers, we investigated machine learning algorithms that find clinical studies with high clinical impact from PubMed®. Our machine learning algorithms use a variety of features including bibliometric features (e.g., citation count), social media attention, journal impact factors, and citation metadata. The algorithms were developed and evaluated with a gold standard composed of 502 high impact clinical studies that are referenced in 11 clinical evidence-based guidelines on the treatment of various diseases. We tested the following hypotheses: (1) our high impact classifier outperforms a state-of-the-art classifier based on citation metadata and citation terms, and PubMed's® relevance sort algorithm; and (2) the performance of our high impact classifier does not decrease significantly after removing proprietary features such as citation count. The mean top 20 precision of our high impact classifier was 34% versus 11% for the state-of-the-art classifier and 4% for PubMed's® relevance sort (p=0.009); and the performance of our high impact classifier did not decrease significantly after removing proprietary features (mean top 20 precision=34% vs. 36%; p=0.085). The high impact classifier, using features such as bibliometrics, social media attention and MEDLINE® metadata, outperformed previous approaches and is a promising alternative to identifying high impact studies for clinical decision support. Copyright © 2017 Elsevier Inc. All rights reserved.

Selection of the best features for leukocytes classification in blood smear microscopic images

NASA Astrophysics Data System (ADS)

Sarrafzadeh, Omid; Rabbani, Hossein; Talebi, Ardeshir; Banaem, Hossein Usefi

2014-03-01

Automatic differential counting of leukocytes provides invaluable information to pathologist for diagnosis and treatment of many diseases. The main objective of this paper is to detect leukocytes from a blood smear microscopic image and classify them into their types: Neutrophil, Eosinophil, Basophil, Lymphocyte and Monocyte using features that pathologists consider to differentiate leukocytes. Features contain color, geometric and texture features. Colors of nucleus and cytoplasm vary among the leukocytes. Lymphocytes have single, large, round or oval and Monocytes have singular convoluted shape nucleus. Nucleus of Eosinophils is divided into 2 segments and nucleus of Neutrophils into 2 to 5 segments. Lymphocytes often have no granules, Monocytes have tiny granules, Neutrophils have fine granules and Eosinophils have large granules in cytoplasm. Six color features is extracted from both nucleus and cytoplasm, 6 geometric features only from nucleus and 6 statistical features and 7 moment invariants features only from cytoplasm of leukocytes. These features are fed to support vector machine (SVM) classifiers with one to one architecture. The results obtained by applying the proposed method on blood smear microscopic image of 10 patients including 149 white blood cells (WBCs) indicate that correct rate for all classifiers are above 93% which is in a higher level in comparison with previous literatures.

Textural features for radar image analysis

NASA Technical Reports Server (NTRS)

Shanmugan, K. S.; Narayanan, V.; Frost, V. S.; Stiles, J. A.; Holtzman, J. C.

1981-01-01

Texture is seen as an important spatial feature useful for identifying objects or regions of interest in an image. While textural features have been widely used in analyzing a variety of photographic images, they have not been used in processing radar images. A procedure for extracting a set of textural features for characterizing small areas in radar images is presented, and it is shown that these features can be used in classifying segments of radar images corresponding to different geological formations.

An integration of minimum local feature representation methods to recognize large variation of foods

NASA Astrophysics Data System (ADS)

Razali, Mohd Norhisham bin; Manshor, Noridayu; Halin, Alfian Abdul; Mustapha, Norwati; Yaakob, Razali

2017-10-01

Local invariant features have shown to be successful in describing object appearances for image classification tasks. Such features are robust towards occlusion and clutter and are also invariant against scale and orientation changes. This makes them suitable for classification tasks with little inter-class similarity and large intra-class difference. In this paper, we propose an integrated representation of the Speeded-Up Robust Feature (SURF) and Scale Invariant Feature Transform (SIFT) descriptors, using late fusion strategy. The proposed representation is used for food recognition from a dataset of food images with complex appearance variations. The Bag of Features (BOF) approach is employed to enhance the discriminative ability of the local features. Firstly, the individual local features are extracted to construct two kinds of visual vocabularies, representing SURF and SIFT. The visual vocabularies are then concatenated and fed into a Linear Support Vector Machine (SVM) to classify the respective food categories. Experimental results demonstrate impressive overall recognition at 82.38% classification accuracy based on the challenging UEC-Food100 dataset.

Mild Depression Detection of College Students: an EEG-Based Solution with Free Viewing Tasks.

PubMed

Li, Xiaowei; Hu, Bin; Shen, Ji; Xu, Tingting; Retcliffe, Martyn

2015-12-01

Depression is a common mental disorder with growing prevalence; however current diagnoses of depression face the problem of patient denial, clinical experience and subjective biases from self-report. By using a combination of linear and nonlinear EEG features in our research, we aim to develop a more accurate and objective approach to depression detection that supports the process of diagnosis and assists the monitoring of risk factors. By classifying EEG features during free viewing task, an accuracy of 99.1%, which is the highest to our knowledge by far, was achieved using kNN classifier to discriminate depressed and non-depressed subjects. Furthermore, through correlation analysis, comparisons of performance on each electrode were discussed on the availability of single channel EEG recording depression detection system. Combined with wearable EEG collecting devices, our method offers the possibility of cost effective wearable ubiquitous system for doctors to monitor their patients with depression, and for normal people to understand their mental states in time.

Local curvature analysis for classifying breast tumors: Preliminary analysis in dedicated breast CT

DOE Office of Scientific and Technical Information (OSTI.GOV)

Lee, Juhun, E-mail: leej15@upmc.edu; Nishikawa, Robert M.; Reiser, Ingrid

2015-09-15

Purpose: The purpose of this study is to measure the effectiveness of local curvature measures as novel image features for classifying breast tumors. Methods: A total of 119 breast lesions from 104 noncontrast dedicated breast computed tomography images of women were used in this study. Volumetric segmentation was done using a seed-based segmentation algorithm and then a triangulated surface was extracted from the resulting segmentation. Total, mean, and Gaussian curvatures were then computed. Normalized curvatures were used as classification features. In addition, traditional image features were also extracted and a forward feature selection scheme was used to select the optimalmore » feature set. Logistic regression was used as a classifier and leave-one-out cross-validation was utilized to evaluate the classification performances of the features. The area under the receiver operating characteristic curve (AUC, area under curve) was used as a figure of merit. Results: Among curvature measures, the normalized total curvature (C{sub T}) showed the best classification performance (AUC of 0.74), while the others showed no classification power individually. Five traditional image features (two shape, two margin, and one texture descriptors) were selected via the feature selection scheme and its resulting classifier achieved an AUC of 0.83. Among those five features, the radial gradient index (RGI), which is a margin descriptor, showed the best classification performance (AUC of 0.73). A classifier combining RGI and C{sub T} yielded an AUC of 0.81, which showed similar performance (i.e., no statistically significant difference) to the classifier with the above five traditional image features. Additional comparisons in AUC values between classifiers using different combinations of traditional image features and C{sub T} were conducted. The results showed that C{sub T} was able to replace the other four image features for the classification task. Conclusions: The normalized curvature measure contains useful information in classifying breast tumors. Using this, one can reduce the number of features in a classifier, which may result in more robust classifiers for different datasets.« less

Detecting epileptic seizure with different feature extracting strategies using robust machine learning classification techniques by applying advance parameter optimization approach.

PubMed

Hussain, Lal

2018-06-01

Epilepsy is a neurological disorder produced due to abnormal excitability of neurons in the brain. The research reveals that brain activity is monitored through electroencephalogram (EEG) of patients suffered from seizure to detect the epileptic seizure. The performance of EEG detection based epilepsy require feature extracting strategies. In this research, we have extracted varying features extracting strategies based on time and frequency domain characteristics, nonlinear, wavelet based entropy and few statistical features. A deeper study was undertaken using novel machine learning classifiers by considering multiple factors. The support vector machine kernels are evaluated based on multiclass kernel and box constraint level. Likewise, for K-nearest neighbors (KNN), we computed the different distance metrics, Neighbor weights and Neighbors. Similarly, the decision trees we tuned the paramours based on maximum splits and split criteria and ensemble classifiers are evaluated based on different ensemble methods and learning rate. For training/testing tenfold Cross validation was employed and performance was evaluated in form of TPR, NPR, PPV, accuracy and AUC. In this research, a deeper analysis approach was performed using diverse features extracting strategies using robust machine learning classifiers with more advanced optimal options. Support Vector Machine linear kernel and KNN with City block distance metric give the overall highest accuracy of 99.5% which was higher than using the default parameters for these classifiers. Moreover, highest separation (AUC = 0.9991, 0.9990) were obtained at different kernel scales using SVM. Additionally, the K-nearest neighbors with inverse squared distance weight give higher performance at different Neighbors. Moreover, to distinguish the postictal heart rate oscillations from epileptic ictal subjects, and highest performance of 100% was obtained using different machine learning classifiers.

Multi-feature classifiers for burst detection in single EEG channels from preterm infants

NASA Astrophysics Data System (ADS)

Navarro, X.; Porée, F.; Kuchenbuch, M.; Chavez, M.; Beuchée, Alain; Carrault, G.

2017-08-01

Objective. The study of electroencephalographic (EEG) bursts in preterm infants provides valuable information about maturation or prognostication after perinatal asphyxia. Over the last two decades, a number of works proposed algorithms to automatically detect EEG bursts in preterm infants, but they were designed for populations under 35 weeks of post menstrual age (PMA). However, as the brain activity evolves rapidly during postnatal life, these solutions might be under-performing with increasing PMA. In this work we focused on preterm infants reaching term ages (PMA  ⩾36 weeks) using multi-feature classification on a single EEG channel. Approach. Five EEG burst detectors relying on different machine learning approaches were compared: logistic regression (LR), linear discriminant analysis (LDA), k-nearest neighbors (kNN), support vector machines (SVM) and thresholding (Th). Classifiers were trained by visually labeled EEG recordings from 14 very preterm infants (born after 28 weeks of gestation) with 36-41 weeks PMA. Main results. The most performing classifiers reached about 95% accuracy (kNN, SVM and LR) whereas Th obtained 84%. Compared to human-automatic agreements, LR provided the highest scores (Cohen’s kappa  =  0.71) using only three EEG features. Applying this classifier in an unlabeled database of 21 infants  ⩾36 weeks PMA, we found that long EEG bursts and short inter-burst periods are characteristic of infants with the highest PMA and weights. Significance. In view of these results, LR-based burst detection could be a suitable tool to study maturation in monitoring or portable devices using a single EEG channel.

Statistical process control using optimized neural networks: a case study.

PubMed

Addeh, Jalil; Ebrahimzadeh, Ata; Azarbad, Milad; Ranaee, Vahid

2014-09-01

The most common statistical process control (SPC) tools employed for monitoring process changes are control charts. A control chart demonstrates that the process has altered by generating an out-of-control signal. This study investigates the design of an accurate system for the control chart patterns (CCPs) recognition in two aspects. First, an efficient system is introduced that includes two main modules: feature extraction module and classifier module. In the feature extraction module, a proper set of shape features and statistical feature are proposed as the efficient characteristics of the patterns. In the classifier module, several neural networks, such as multilayer perceptron, probabilistic neural network and radial basis function are investigated. Based on an experimental study, the best classifier is chosen in order to recognize the CCPs. Second, a hybrid heuristic recognition system is introduced based on cuckoo optimization algorithm (COA) algorithm to improve the generalization performance of the classifier. The simulation results show that the proposed algorithm has high recognition accuracy. Copyright © 2013 ISA. Published by Elsevier Ltd. All rights reserved.

Automatic classification for mammogram backgrounds based on bi-rads complexity definition and on a multi content analysis framework

NASA Astrophysics Data System (ADS)

Wu, Jie; Besnehard, Quentin; Marchessoux, Cédric

2011-03-01

Clinical studies for the validation of new medical imaging devices require hundreds of images. An important step in creating and tuning the study protocol is the classification of images into "difficult" and "easy" cases. This consists of classifying the image based on features like the complexity of the background, the visibility of the disease (lesions). Therefore, an automatic medical background classification tool for mammograms would help for such clinical studies. This classification tool is based on a multi-content analysis framework (MCA) which was firstly developed to recognize image content of computer screen shots. With the implementation of new texture features and a defined breast density scale, the MCA framework is able to automatically classify digital mammograms with a satisfying accuracy. BI-RADS (Breast Imaging Reporting Data System) density scale is used for grouping the mammograms, which standardizes the mammography reporting terminology and assessment and recommendation categories. Selected features are input into a decision tree classification scheme in MCA framework, which is the so called "weak classifier" (any classifier with a global error rate below 50%). With the AdaBoost iteration algorithm, these "weak classifiers" are combined into a "strong classifier" (a classifier with a low global error rate) for classifying one category. The results of classification for one "strong classifier" show the good accuracy with the high true positive rates. For the four categories the results are: TP=90.38%, TN=67.88%, FP=32.12% and FN =9.62%.

Comparison of Different Features and Classifiers for Driver Fatigue Detection Based on a Single EEG Channel

PubMed Central

2017-01-01

Driver fatigue has become an important factor to traffic accidents worldwide, and effective detection of driver fatigue has major significance for public health. The purpose method employs entropy measures for feature extraction from a single electroencephalogram (EEG) channel. Four types of entropies measures, sample entropy (SE), fuzzy entropy (FE), approximate entropy (AE), and spectral entropy (PE), were deployed for the analysis of original EEG signal and compared by ten state-of-the-art classifiers. Results indicate that optimal performance of single channel is achieved using a combination of channel CP4, feature FE, and classifier Random Forest (RF). The highest accuracy can be up to 96.6%, which has been able to meet the needs of real applications. The best combination of channel + features + classifier is subject-specific. In this work, the accuracy of FE as the feature is far greater than the Acc of other features. The accuracy using classifier RF is the best, while that of classifier SVM with linear kernel is the worst. The impact of channel selection on the Acc is larger. The performance of various channels is very different. PMID:28255330

Comparison of Different Features and Classifiers for Driver Fatigue Detection Based on a Single EEG Channel.

PubMed

Hu, Jianfeng

2017-01-01

Driver fatigue has become an important factor to traffic accidents worldwide, and effective detection of driver fatigue has major significance for public health. The purpose method employs entropy measures for feature extraction from a single electroencephalogram (EEG) channel. Four types of entropies measures, sample entropy (SE), fuzzy entropy (FE), approximate entropy (AE), and spectral entropy (PE), were deployed for the analysis of original EEG signal and compared by ten state-of-the-art classifiers. Results indicate that optimal performance of single channel is achieved using a combination of channel CP4, feature FE, and classifier Random Forest (RF). The highest accuracy can be up to 96.6%, which has been able to meet the needs of real applications. The best combination of channel + features + classifier is subject-specific. In this work, the accuracy of FE as the feature is far greater than the Acc of other features. The accuracy using classifier RF is the best, while that of classifier SVM with linear kernel is the worst. The impact of channel selection on the Acc is larger. The performance of various channels is very different.

Non-invasive classification of gas-liquid two-phase horizontal flow regimes using an ultrasonic Doppler sensor and a neural network

NASA Astrophysics Data System (ADS)

Musa Abbagoni, Baba; Yeung, Hoi

2016-08-01

The identification of flow pattern is a key issue in multiphase flow which is encountered in the petrochemical industry. It is difficult to identify the gas-liquid flow regimes objectively with the gas-liquid two-phase flow. This paper presents the feasibility of a clamp-on instrument for an objective flow regime classification of two-phase flow using an ultrasonic Doppler sensor and an artificial neural network, which records and processes the ultrasonic signals reflected from the two-phase flow. Experimental data is obtained on a horizontal test rig with a total pipe length of 21 m and 5.08 cm internal diameter carrying air-water two-phase flow under slug, elongated bubble, stratified-wavy and, stratified flow regimes. Multilayer perceptron neural networks (MLPNNs) are used to develop the classification model. The classifier requires features as an input which is representative of the signals. Ultrasound signal features are extracted by applying both power spectral density (PSD) and discrete wavelet transform (DWT) methods to the flow signals. A classification scheme of ‘1-of-C coding method for classification’ was adopted to classify features extracted into one of four flow regime categories. To improve the performance of the flow regime classifier network, a second level neural network was incorporated by using the output of a first level networks feature as an input feature. The addition of the two network models provided a combined neural network model which has achieved a higher accuracy than single neural network models. Classification accuracies are evaluated in the form of both the PSD and DWT features. The success rates of the two models are: (1) using PSD features, the classifier missed 3 datasets out of 24 test datasets of the classification and scored 87.5% accuracy; (2) with the DWT features, the network misclassified only one data point and it was able to classify the flow patterns up to 95.8% accuracy. This approach has demonstrated the success of a clamp-on ultrasound sensor for flow regime classification that would be possible in industry practice. It is considerably more promising than other techniques as it uses a non-invasive and non-radioactive sensor.

The design and performance characteristics of a cellular logic 3-D image classification processor

NASA Astrophysics Data System (ADS)

Ankeney, L. A.

1981-04-01

The introduction of high resolution scanning laser radar systems which are capable of collecting range and reflectivity images, is predicted to significantly influence the development of processors capable of performing autonomous target classification tasks. Actively sensed range images are shown to be superior to passively collected infrared images in both image stability and information content. An illustrated tutorial introduces cellular logic (neighborhood) transformations and two and three dimensional erosion and dilation operations which are used for noise filters and geometric shape measurement. A unique 'cookbook' approach to selecting a sequence of neighborhood transformations suitable for object measurement is developed and related to false alarm rate and algorithm effectiveness measures. The cookbook design approach is used to develop an algorithm to classify objects based upon their 3-D geometrical features. A Monte Carlo performance analysis is used to demonstrate the utility of the design approach by characterizing the ability of the algorithm to classify randomly positioned three dimensional objects in the presence of additive noise, scale variations, and other forms of image distortion.

A multiple-point spatially weighted k-NN method for object-based classification

NASA Astrophysics Data System (ADS)

Tang, Yunwei; Jing, Linhai; Li, Hui; Atkinson, Peter M.

2016-10-01

Object-based classification, commonly referred to as object-based image analysis (OBIA), is now commonly regarded as able to produce more appealing classification maps, often of greater accuracy, than pixel-based classification and its application is now widespread. Therefore, improvement of OBIA using spatial techniques is of great interest. In this paper, multiple-point statistics (MPS) is proposed for object-based classification enhancement in the form of a new multiple-point k-nearest neighbour (k-NN) classification method (MPk-NN). The proposed method first utilises a training image derived from a pre-classified map to characterise the spatial correlation between multiple points of land cover classes. The MPS borrows spatial structures from other parts of the training image, and then incorporates this spatial information, in the form of multiple-point probabilities, into the k-NN classifier. Two satellite sensor images with a fine spatial resolution were selected to evaluate the new method. One is an IKONOS image of the Beijing urban area and the other is a WorldView-2 image of the Wolong mountainous area, in China. The images were object-based classified using the MPk-NN method and several alternatives, including the k-NN, the geostatistically weighted k-NN, the Bayesian method, the decision tree classifier (DTC), and the support vector machine classifier (SVM). It was demonstrated that the new spatial weighting based on MPS can achieve greater classification accuracy relative to the alternatives and it is, thus, recommended as appropriate for object-based classification.

Multi-objective evolutionary algorithms for fuzzy classification in survival prediction.

PubMed

Jiménez, Fernando; Sánchez, Gracia; Juárez, José M

2014-03-01

This paper presents a novel rule-based fuzzy classification methodology for survival/mortality prediction in severe burnt patients. Due to the ethical aspects involved in this medical scenario, physicians tend not to accept a computer-based evaluation unless they understand why and how such a recommendation is given. Therefore, any fuzzy classifier model must be both accurate and interpretable. The proposed methodology is a three-step process: (1) multi-objective constrained optimization of a patient's data set, using Pareto-based elitist multi-objective evolutionary algorithms to maximize accuracy and minimize the complexity (number of rules) of classifiers, subject to interpretability constraints; this step produces a set of alternative (Pareto) classifiers; (2) linguistic labeling, which assigns a linguistic label to each fuzzy set of the classifiers; this step is essential to the interpretability of the classifiers; (3) decision making, whereby a classifier is chosen, if it is satisfactory, according to the preferences of the decision maker. If no classifier is satisfactory for the decision maker, the process starts again in step (1) with a different input parameter set. The performance of three multi-objective evolutionary algorithms, niched pre-selection multi-objective algorithm, elitist Pareto-based multi-objective evolutionary algorithm for diversity reinforcement (ENORA) and the non-dominated sorting genetic algorithm (NSGA-II), was tested using a patient's data set from an intensive care burn unit and a standard machine learning data set from an standard machine learning repository. The results are compared using the hypervolume multi-objective metric. Besides, the results have been compared with other non-evolutionary techniques and validated with a multi-objective cross-validation technique. Our proposal improves the classification rate obtained by other non-evolutionary techniques (decision trees, artificial neural networks, Naive Bayes, and case-based reasoning) obtaining with ENORA a classification rate of 0.9298, specificity of 0.9385, and sensitivity of 0.9364, with 14.2 interpretable fuzzy rules on average. Our proposal improves the accuracy and interpretability of the classifiers, compared with other non-evolutionary techniques. We also conclude that ENORA outperforms niched pre-selection and NSGA-II algorithms. Moreover, given that our multi-objective evolutionary methodology is non-combinational based on real parameter optimization, the time cost is significantly reduced compared with other evolutionary approaches existing in literature based on combinational optimization. Copyright © 2014 Elsevier B.V. All rights reserved.

Managing Highway Maintenance: Instructor's Manual for Management by Objectives Review, Unit 11, All Levels.

ERIC Educational Resources Information Center

Federal Highway Administration (DOT), Washington, DC. Offices of Research and Development.

Part of the series "Managing Highway Maintenance," the unit is designed for the training group leader and contains selected highlights and suggested discussion questions from six units of training: maintenance activities, work units, and classifying work; maintenance feature inventories; how to conduct a maintenance feature inventory;…

Testing random forest classification for identifying lava flows and mapping age groups on a single Landsat 8 image

NASA Astrophysics Data System (ADS)

Li, Long; Solana, Carmen; Canters, Frank; Kervyn, Matthieu

2017-10-01

Mapping lava flows using satellite images is an important application of remote sensing in volcanology. Several volcanoes have been mapped through remote sensing using a wide range of data, from optical to thermal infrared and radar images, using techniques such as manual mapping, supervised/unsupervised classification, and elevation subtraction. So far, spectral-based mapping applications mainly focus on the use of traditional pixel-based classifiers, without much investigation into the added value of object-based approaches and into advantages of using machine learning algorithms. In this study, Nyamuragira, characterized by a series of > 20 overlapping lava flows erupted over the last century, was used as a case study. The random forest classifier was tested to map lava flows based on pixels and objects. Image classification was conducted for the 20 individual flows and for 8 groups of flows of similar age using a Landsat 8 image and a DEM of the volcano, both at 30-meter spatial resolution. Results show that object-based classification produces maps with continuous and homogeneous lava surfaces, in agreement with the physical characteristics of lava flows, while lava flows mapped through the pixel-based classification are heterogeneous and fragmented including much "salt and pepper noise". In terms of accuracy, both pixel-based and object-based classification performs well but the former results in higher accuracies than the latter except for mapping lava flow age groups without using topographic features. It is concluded that despite spectral similarity, lava flows of contrasting age can be well discriminated and mapped by means of image classification. The classification approach demonstrated in this study only requires easily accessible image data and can be applied to other volcanoes as well if there is sufficient information to calibrate the mapping.

Classification of epileptic EEG signals based on simple random sampling and sequential feature selection.

PubMed

Ghayab, Hadi Ratham Al; Li, Yan; Abdulla, Shahab; Diykh, Mohammed; Wan, Xiangkui

2016-06-01

Electroencephalogram (EEG) signals are used broadly in the medical fields. The main applications of EEG signals are the diagnosis and treatment of diseases such as epilepsy, Alzheimer, sleep problems and so on. This paper presents a new method which extracts and selects features from multi-channel EEG signals. This research focuses on three main points. Firstly, simple random sampling (SRS) technique is used to extract features from the time domain of EEG signals. Secondly, the sequential feature selection (SFS) algorithm is applied to select the key features and to reduce the dimensionality of the data. Finally, the selected features are forwarded to a least square support vector machine (LS_SVM) classifier to classify the EEG signals. The LS_SVM classifier classified the features which are extracted and selected from the SRS and the SFS. The experimental results show that the method achieves 99.90, 99.80 and 100 % for classification accuracy, sensitivity and specificity, respectively.

Classification of Liss IV Imagery Using Decision Tree Methods

NASA Astrophysics Data System (ADS)

Verma, Amit Kumar; Garg, P. K.; Prasad, K. S. Hari; Dadhwal, V. K.

2016-06-01

Image classification is a compulsory step in any remote sensing research. Classification uses the spectral information represented by the digital numbers in one or more spectral bands and attempts to classify each individual pixel based on this spectral information. Crop classification is the main concern of remote sensing applications for developing sustainable agriculture system. Vegetation indices computed from satellite images gives a good indication of the presence of vegetation. It is an indicator that describes the greenness, density and health of vegetation. Texture is also an important characteristics which is used to identifying objects or region of interest is an image. This paper illustrate the use of decision tree method to classify the land in to crop land and non-crop land and to classify different crops. In this paper we evaluate the possibility of crop classification using an integrated approach methods based on texture property with different vegetation indices for single date LISS IV sensor 5.8 meter high spatial resolution data. Eleven vegetation indices (NDVI, DVI, GEMI, GNDVI, MSAVI2, NDWI, NG, NR, NNIR, OSAVI and VI green) has been generated using green, red and NIR band and then image is classified using decision tree method. The other approach is used integration of texture feature (mean, variance, kurtosis and skewness) with these vegetation indices. A comparison has been done between these two methods. The results indicate that inclusion of textural feature with vegetation indices can be effectively implemented to produce classifiedmaps with 8.33% higher accuracy for Indian satellite IRS-P6, LISS IV sensor images.

Evolutionary optimization of radial basis function classifiers for data mining applications.

PubMed

Buchtala, Oliver; Klimek, Manuel; Sick, Bernhard

2005-10-01

In many data mining applications that address classification problems, feature and model selection are considered as key tasks. That is, appropriate input features of the classifier must be selected from a given (and often large) set of possible features and structure parameters of the classifier must be adapted with respect to these features and a given data set. This paper describes an evolutionary algorithm (EA) that performs feature and model selection simultaneously for radial basis function (RBF) classifiers. In order to reduce the optimization effort, various techniques are integrated that accelerate and improve the EA significantly: hybrid training of RBF networks, lazy evaluation, consideration of soft constraints by means of penalty terms, and temperature-based adaptive control of the EA. The feasibility and the benefits of the approach are demonstrated by means of four data mining problems: intrusion detection in computer networks, biometric signature verification, customer acquisition with direct marketing methods, and optimization of chemical production processes. It is shown that, compared to earlier EA-based RBF optimization techniques, the runtime is reduced by up to 99% while error rates are lowered by up to 86%, depending on the application. The algorithm is independent of specific applications so that many ideas and solutions can be transferred to other classifier paradigms.

E-Nose Vapor Identification Based on Dempster-Shafer Fusion of Multiple Classifiers

NASA Technical Reports Server (NTRS)

Li, Winston; Leung, Henry; Kwan, Chiman; Linnell, Bruce R.

2005-01-01

Electronic nose (e-nose) vapor identification is an efficient approach to monitor air contaminants in space stations and shuttles in order to ensure the health and safety of astronauts. Data preprocessing (measurement denoising and feature extraction) and pattern classification are important components of an e-nose system. In this paper, a wavelet-based denoising method is applied to filter the noisy sensor measurements. Transient-state features are then extracted from the denoised sensor measurements, and are used to train multiple classifiers such as multi-layer perceptions (MLP), support vector machines (SVM), k nearest neighbor (KNN), and Parzen classifier. The Dempster-Shafer (DS) technique is used at the end to fuse the results of the multiple classifiers to get the final classification. Experimental analysis based on real vapor data shows that the wavelet denoising method can remove both random noise and outliers successfully, and the classification rate can be improved by using classifier fusion.

Metrics and textural features of MRI diffusion to improve classification of pediatric posterior fossa tumors.

PubMed

Rodriguez Gutierrez, D; Awwad, A; Meijer, L; Manita, M; Jaspan, T; Dineen, R A; Grundy, R G; Auer, D P

2014-05-01

Qualitative radiologic MR imaging review affords limited differentiation among types of pediatric posterior fossa brain tumors and cannot detect histologic or molecular subtypes, which could help to stratify treatment. This study aimed to improve current posterior fossa discrimination of histologic tumor type by using support vector machine classifiers on quantitative MR imaging features. This retrospective study included preoperative MRI in 40 children with posterior fossa tumors (17 medulloblastomas, 16 pilocytic astrocytomas, and 7 ependymomas). Shape, histogram, and textural features were computed from contrast-enhanced T2WI and T1WI and diffusivity (ADC) maps. Combinations of features were used to train tumor-type-specific classifiers for medulloblastoma, pilocytic astrocytoma, and ependymoma types in separation and as a joint posterior fossa classifier. A tumor-subtype classifier was also produced for classic medulloblastoma. The performance of different classifiers was assessed and compared by using randomly selected subsets of training and test data. ADC histogram features (25th and 75th percentiles and skewness) yielded the best classification of tumor type (on average >95.8% of medulloblastomas, >96.9% of pilocytic astrocytomas, and >94.3% of ependymomas by using 8 training samples). The resulting joint posterior fossa classifier correctly assigned >91.4% of the posterior fossa tumors. For subtype classification, 89.4% of classic medulloblastomas were correctly classified on the basis of ADC texture features extracted from the Gray-Level Co-Occurence Matrix. Support vector machine-based classifiers using ADC histogram features yielded very good discrimination among pediatric posterior fossa tumor types, and ADC textural features show promise for further subtype discrimination. These findings suggest an added diagnostic value of quantitative feature analysis of diffusion MR imaging in pediatric neuro-oncology. © 2014 by American Journal of Neuroradiology.

Developing a radiomics framework for classifying non-small cell lung carcinoma subtypes

NASA Astrophysics Data System (ADS)

Yu, Dongdong; Zang, Yali; Dong, Di; Zhou, Mu; Gevaert, Olivier; Fang, Mengjie; Shi, Jingyun; Tian, Jie

2017-03-01

Patient-targeted treatment of non-small cell lung carcinoma (NSCLC) has been well documented according to the histologic subtypes over the past decade. In parallel, recent development of quantitative image biomarkers has recently been highlighted as important diagnostic tools to facilitate histological subtype classification. In this study, we present a radiomics analysis that classifies the adenocarcinoma (ADC) and squamous cell carcinoma (SqCC). We extract 52-dimensional, CT-based features (7 statistical features and 45 image texture features) to represent each nodule. We evaluate our approach on a clinical dataset including 324 ADCs and 110 SqCCs patients with CT image scans. Classification of these features is performed with four different machine-learning classifiers including Support Vector Machines with Radial Basis Function kernel (RBF-SVM), Random forest (RF), K-nearest neighbor (KNN), and RUSBoost algorithms. To improve the classifiers' performance, optimal feature subset is selected from the original feature set by using an iterative forward inclusion and backward eliminating algorithm. Extensive experimental results demonstrate that radiomics features achieve encouraging classification results on both complete feature set (AUC=0.89) and optimal feature subset (AUC=0.91).

A comparison of supervised classification methods for the prediction of substrate type using multibeam acoustic and legacy grain-size data.

PubMed

Stephens, David; Diesing, Markus

2014-01-01

Detailed seabed substrate maps are increasingly in demand for effective planning and management of marine ecosystems and resources. It has become common to use remotely sensed multibeam echosounder data in the form of bathymetry and acoustic backscatter in conjunction with ground-truth sampling data to inform the mapping of seabed substrates. Whilst, until recently, such data sets have typically been classified by expert interpretation, it is now obvious that more objective, faster and repeatable methods of seabed classification are required. This study compares the performances of a range of supervised classification techniques for predicting substrate type from multibeam echosounder data. The study area is located in the North Sea, off the north-east coast of England. A total of 258 ground-truth samples were classified into four substrate classes. Multibeam bathymetry and backscatter data, and a range of secondary features derived from these datasets were used in this study. Six supervised classification techniques were tested: Classification Trees, Support Vector Machines, k-Nearest Neighbour, Neural Networks, Random Forest and Naive Bayes. Each classifier was trained multiple times using different input features, including i) the two primary features of bathymetry and backscatter, ii) a subset of the features chosen by a feature selection process and iii) all of the input features. The predictive performances of the models were validated using a separate test set of ground-truth samples. The statistical significance of model performances relative to a simple baseline model (Nearest Neighbour predictions on bathymetry and backscatter) were tested to assess the benefits of using more sophisticated approaches. The best performing models were tree based methods and Naive Bayes which achieved accuracies of around 0.8 and kappa coefficients of up to 0.5 on the test set. The models that used all input features didn't generally perform well, highlighting the need for some means of feature selection.

Brownian motion curve-based textural classification and its application in cancer diagnosis.

PubMed

Mookiah, Muthu Rama Krishnan; Shah, Pratik; Chakraborty, Chandan; Ray, Ajoy K

2011-06-01

To develop an automated diagnostic methodology based on textural features of the oral mucosal epithelium to discriminate normal and oral submucous fibrosis (OSF). A total of 83 normal and 29 OSF images from histopathologic sections of the oral mucosa are considered. The proposed diagnostic mechanism consists of two parts: feature extraction using Brownian motion curve (BMC) and design ofa suitable classifier. The discrimination ability of the features has been substantiated by statistical tests. An error back-propagation neural network (BPNN) is used to classify OSF vs. normal. In development of an automated oral cancer diagnostic module, BMC has played an important role in characterizing textural features of the oral images. Fisher's linear discriminant analysis yields 100% sensitivity and 85% specificity, whereas BPNN leads to 92.31% sensitivity and 100% specificity, respectively. In addition to intensity and morphology-based features, textural features are also very important, especially in histopathologic diagnosis of oral cancer. In view of this, a set of textural features are extracted using the BMC for the diagnosis of OSF. Finally, a textural classifier is designed using BPNN, which leads to a diagnostic performance with 96.43% accuracy. (Anal Quant

Computer-aided classification of mammographic masses using the deep learning technology: a preliminary study

NASA Astrophysics Data System (ADS)

Qiu, Yuchen; Yan, Shiju; Tan, Maxine; Cheng, Samuel; Liu, Hong; Zheng, Bin

2016-03-01

Although mammography is the only clinically acceptable imaging modality used in the population-based breast cancer screening, its efficacy is quite controversy. One of the major challenges is how to help radiologists more accurately classify between benign and malignant lesions. The purpose of this study is to investigate a new mammographic mass classification scheme based on a deep learning method. In this study, we used an image dataset involving 560 regions of interest (ROIs) extracted from digital mammograms, which includes 280 malignant and 280 benign mass ROIs, respectively. An eight layer deep learning network was applied, which employs three pairs of convolution-max-pooling layers for automatic feature extraction and a multiple layer perception (MLP) classifier for feature categorization. In order to improve robustness of selected features, each convolution layer is connected with a max-pooling layer. A number of 20, 10, and 5 feature maps were utilized for the 1st, 2nd and 3rd convolution layer, respectively. The convolution networks are followed by a MLP classifier, which generates a classification score to predict likelihood of a ROI depicting a malignant mass. Among 560 ROIs, 420 ROIs were used as a training dataset and the remaining 140 ROIs were used as a validation dataset. The result shows that the new deep learning based classifier yielded an area under the receiver operation characteristic curve (AUC) of 0.810+/-0.036. This study demonstrated the potential superiority of using a deep learning based classifier to distinguish malignant and benign breast masses without segmenting the lesions and extracting the pre-defined image features.

Diagnosis of multiple sclerosis from EEG signals using nonlinear methods.

PubMed

Torabi, Ali; Daliri, Mohammad Reza; Sabzposhan, Seyyed Hojjat

2017-12-01

EEG signals have essential and important information about the brain and neural diseases. The main purpose of this study is classifying two groups of healthy volunteers and Multiple Sclerosis (MS) patients using nonlinear features of EEG signals while performing cognitive tasks. EEG signals were recorded when users were doing two different attentional tasks. One of the tasks was based on detecting a desired change in color luminance and the other task was based on detecting a desired change in direction of motion. EEG signals were analyzed in two ways: EEG signals analysis without rhythms decomposition and EEG sub-bands analysis. After recording and preprocessing, time delay embedding method was used for state space reconstruction; embedding parameters were determined for original signals and their sub-bands. Afterwards nonlinear methods were used in feature extraction phase. To reduce the feature dimension, scalar feature selections were done by using T-test and Bhattacharyya criteria. Then, the data were classified using linear support vector machines (SVM) and k-nearest neighbor (KNN) method. The best combination of the criteria and classifiers was determined for each task by comparing performances. For both tasks, the best results were achieved by using T-test criterion and SVM classifier. For the direction-based and the color-luminance-based tasks, maximum classification performances were 93.08 and 79.79% respectively which were reached by using optimal set of features. Our results show that the nonlinear dynamic features of EEG signals seem to be useful and effective in MS diseases diagnosis.

Non-Trivial Feature Derivation for Intensifying Feature Detection Using LIDAR Datasets Through Allometric Aggregation Data Analysis Applying Diffused Hierarchical Clustering for Discriminating Agricultural Land Cover in Portions of Northern Mindanao, Philippines

NASA Astrophysics Data System (ADS)

Villar, Ricardo G.; Pelayo, Jigg L.; Mozo, Ray Mari N.; Salig, James B., Jr.; Bantugan, Jojemar

2016-06-01

Leaning on the derived results conducted by Central Mindanao University Phil-LiDAR 2.B.11 Image Processing Component, the paper attempts to provides the application of the Light Detection and Ranging (LiDAR) derived products in arriving quality Landcover classification considering the theoretical approach of data analysis principles to minimize the common problems in image classification. These are misclassification of objects and the non-distinguishable interpretation of pixelated features that results to confusion of class objects due to their closely-related spectral resemblance, unbalance saturation of RGB information is a challenged at the same time. Only low density LiDAR point cloud data is exploited in the research denotes as 2 pts/m2 of accuracy which bring forth essential derived information such as textures and matrices (number of returns, intensity textures, nDSM, etc.) in the intention of pursuing the conditions for selection characteristic. A novel approach that takes gain of the idea of object-based image analysis and the principle of allometric relation of two or more observables which are aggregated for each acquisition of datasets for establishing a proportionality function for data-partioning. In separating two or more data sets in distinct regions in a feature space of distributions, non-trivial computations for fitting distribution were employed to formulate the ideal hyperplane. Achieving the distribution computations, allometric relations were evaluated and match with the necessary rotation, scaling and transformation techniques to find applicable border conditions. Thus, a customized hybrid feature was developed and embedded in every object class feature to be used as classifier with employed hierarchical clustering strategy for cross-examining and filtering features. This features are boost using machine learning algorithms as trainable sets of information for a more competent feature detection. The product classification in this investigation was compared to a classification based on conventional object-oriented approach promoting straight-forward functionalities of the software eCognition. A compelling rise of efficiency in the overall accuracy (74.4% to 93.4%) and kappa index of agreement (70.5% to 91.7%) is noticeable based on the initial process. Nevertheless, having low-dense LiDAR dataset could be enough in generating exponential increase of performance in accuracy.

EEG Negativity in Fixations Used for Gaze-Based Control: Toward Converting Intentions into Actions with an Eye-Brain-Computer Interface

PubMed Central

Shishkin, Sergei L.; Nuzhdin, Yuri O.; Svirin, Evgeny P.; Trofimov, Alexander G.; Fedorova, Anastasia A.; Kozyrskiy, Bogdan L.; Velichkovsky, Boris M.

2016-01-01

We usually look at an object when we are going to manipulate it. Thus, eye tracking can be used to communicate intended actions. An effective human-machine interface, however, should be able to differentiate intentional and spontaneous eye movements. We report an electroencephalogram (EEG) marker that differentiates gaze fixations used for control from spontaneous fixations involved in visual exploration. Eight healthy participants played a game with their eye movements only. Their gaze-synchronized EEG data (fixation-related potentials, FRPs) were collected during game's control-on and control-off conditions. A slow negative wave with a maximum in the parietooccipital region was present in each participant's averaged FRPs in the control-on conditions and was absent or had much lower amplitude in the control-off condition. This wave was similar but not identical to stimulus-preceding negativity, a slow negative wave that can be observed during feedback expectation. Classification of intentional vs. spontaneous fixations was based on amplitude features from 13 EEG channels using 300 ms length segments free from electrooculogram contamination (200–500 ms relative to the fixation onset). For the first fixations in the fixation triplets required to make moves in the game, classified against control-off data, a committee of greedy classifiers provided 0.90 ± 0.07 specificity and 0.38 ± 0.14 sensitivity. Similar (slightly lower) results were obtained for the shrinkage Linear Discriminate Analysis (LDA) classifier. The second and third fixations in the triplets were classified at lower rate. We expect that, with improved feature sets and classifiers, a hybrid dwell-based Eye-Brain-Computer Interface (EBCI) can be built using the FRP difference between the intended and spontaneous fixations. If this direction of BCI development will be successful, such a multimodal interface may improve the fluency of interaction and can possibly become the basis for a new input device for paralyzed and healthy users, the EBCI “Wish Mouse.” PMID:27917105

A dictionary learning approach for human sperm heads classification.

PubMed

Shaker, Fariba; Monadjemi, S Amirhassan; Alirezaie, Javad; Naghsh-Nilchi, Ahmad Reza

2017-12-01

To diagnose infertility in men, semen analysis is conducted in which sperm morphology is one of the factors that are evaluated. Since manual assessment of sperm morphology is time-consuming and subjective, automatic classification methods are being developed. Automatic classification of sperm heads is a complicated task due to the intra-class differences and inter-class similarities of class objects. In this research, a Dictionary Learning (DL) technique is utilized to construct a dictionary of sperm head shapes. This dictionary is used to classify the sperm heads into four different classes. Square patches are extracted from the sperm head images. Columnized patches from each class of sperm are used to learn class-specific dictionaries. The patches from a test image are reconstructed using each class-specific dictionary and the overall reconstruction error for each class is used to select the best matching class. Average accuracy, precision, recall, and F-score are used to evaluate the classification method. The method is evaluated using two publicly available datasets of human sperm head shapes. The proposed DL based method achieved an average accuracy of 92.2% on the HuSHeM dataset, and an average recall of 62% on the SCIAN-MorphoSpermGS dataset. The results show a significant improvement compared to a previously published shape-feature-based method. We have achieved high-performance results. In addition, our proposed approach offers a more balanced classifier in which all four classes are recognized with high precision and recall. In this paper, we use a Dictionary Learning approach in classifying human sperm heads. It is shown that the Dictionary Learning method is far more effective in classifying human sperm heads than classifiers using shape-based features. Also, a dataset of human sperm head shapes is introduced to facilitate future research. Copyright © 2017 Elsevier Ltd. All rights reserved.

Model-based analysis of pattern motion processing in mouse primary visual cortex

PubMed Central

Muir, Dylan R.; Roth, Morgane M.; Helmchen, Fritjof; Kampa, Björn M.

2015-01-01

Neurons in sensory areas of neocortex exhibit responses tuned to specific features of the environment. In visual cortex, information about features such as edges or textures with particular orientations must be integrated to recognize a visual scene or object. Connectivity studies in rodent cortex have revealed that neurons make specific connections within sub-networks sharing common input tuning. In principle, this sub-network architecture enables local cortical circuits to integrate sensory information. However, whether feature integration indeed occurs locally in rodent primary sensory areas has not been examined directly. We studied local integration of sensory features in primary visual cortex (V1) of the mouse by presenting drifting grating and plaid stimuli, while recording the activity of neuronal populations with two-photon calcium imaging. Using a Bayesian model-based analysis framework, we classified single-cell responses as being selective for either individual grating components or for moving plaid patterns. Rather than relying on trial-averaged responses, our model-based framework takes into account single-trial responses and can easily be extended to consider any number of arbitrary predictive models. Our analysis method was able to successfully classify significantly more responses than traditional partial correlation (PC) analysis, and provides a rigorous statistical framework to rank any number of models and reject poorly performing models. We also found a large proportion of cells that respond strongly to only one stimulus class. In addition, a quarter of selectively responding neurons had more complex responses that could not be explained by any simple integration model. Our results show that a broad range of pattern integration processes already take place at the level of V1. This diversity of integration is consistent with processing of visual inputs by local sub-networks within V1 that are tuned to combinations of sensory features. PMID:26300738

Morphological and wavelet features towards sonographic thyroid nodules evaluation.

PubMed

Tsantis, Stavros; Dimitropoulos, Nikos; Cavouras, Dionisis; Nikiforidis, George

2009-03-01

This paper presents a computer-based classification scheme that utilized various morphological and novel wavelet-based features towards malignancy risk evaluation of thyroid nodules in ultrasonography. The study comprised 85 ultrasound images-patients that were cytological confirmed (54 low-risk and 31 high-risk). A set of 20 features (12 based on nodules boundary shape and 8 based on wavelet local maxima located within each nodule) has been generated. Two powerful pattern recognition algorithms (support vector machines and probabilistic neural networks) have been designed and developed in order to quantify the power of differentiation of the introduced features. A comparative study has also been held, in order to estimate the impact speckle had onto the classification procedure. The diagnostic sensitivity and specificity of both classifiers was made by means of receiver operating characteristics (ROC) analysis. In the speckle-free feature set, the area under the ROC curve was 0.96 for the support vector machines classifier whereas for the probabilistic neural networks was 0.91. In the feature set with speckle, the corresponding areas under the ROC curves were 0.88 and 0.86 respectively for the two classifiers. The proposed features can increase the classification accuracy and decrease the rate of missing and misdiagnosis in thyroid cancer control.

Automated oral cancer identification using histopathological images: a hybrid feature extraction paradigm.

PubMed

Krishnan, M Muthu Rama; Venkatraghavan, Vikram; Acharya, U Rajendra; Pal, Mousumi; Paul, Ranjan Rashmi; Min, Lim Choo; Ray, Ajoy Kumar; Chatterjee, Jyotirmoy; Chakraborty, Chandan

2012-02-01

Oral cancer (OC) is the sixth most common cancer in the world. In India it is the most common malignant neoplasm. Histopathological images have widely been used in the differential diagnosis of normal, oral precancerous (oral sub-mucous fibrosis (OSF)) and cancer lesions. However, this technique is limited by subjective interpretations and less accurate diagnosis. The objective of this work is to improve the classification accuracy based on textural features in the development of a computer assisted screening of OSF. The approach introduced here is to grade the histopathological tissue sections into normal, OSF without Dysplasia (OSFWD) and OSF with Dysplasia (OSFD), which would help the oral onco-pathologists to screen the subjects rapidly. The biopsy sections are stained with H&E. The optical density of the pixels in the light microscopic images is recorded and represented as matrix quantized as integers from 0 to 255 for each fundamental color (Red, Green, Blue), resulting in a M×N×3 matrix of integers. Depending on either normal or OSF condition, the image has various granular structures which are self similar patterns at different scales termed "texture". We have extracted these textural changes using Higher Order Spectra (HOS), Local Binary Pattern (LBP), and Laws Texture Energy (LTE) from the histopathological images (normal, OSFWD and OSFD). These feature vectors were fed to five different classifiers: Decision Tree (DT), Sugeno Fuzzy, Gaussian Mixture Model (GMM), K-Nearest Neighbor (K-NN), Radial Basis Probabilistic Neural Network (RBPNN) to select the best classifier. Our results show that combination of texture and HOS features coupled with Fuzzy classifier resulted in 95.7% accuracy, sensitivity and specificity of 94.5% and 98.8% respectively. Finally, we have proposed a novel integrated index called Oral Malignancy Index (OMI) using the HOS, LBP, LTE features, to diagnose benign or malignant tissues using just one number. We hope that this OMI can help the clinicians in making a faster and more objective detection of benign/malignant oral lesions. Copyright © 2011 Elsevier Ltd. All rights reserved.

Feature Selection and Parameters Optimization of SVM Using Particle Swarm Optimization for Fault Classification in Power Distribution Systems.

PubMed

Cho, Ming-Yuan; Hoang, Thi Thom

2017-01-01

Fast and accurate fault classification is essential to power system operations. In this paper, in order to classify electrical faults in radial distribution systems, a particle swarm optimization (PSO) based support vector machine (SVM) classifier has been proposed. The proposed PSO based SVM classifier is able to select appropriate input features and optimize SVM parameters to increase classification accuracy. Further, a time-domain reflectometry (TDR) method with a pseudorandom binary sequence (PRBS) stimulus has been used to generate a dataset for purposes of classification. The proposed technique has been tested on a typical radial distribution network to identify ten different types of faults considering 12 given input features generated by using Simulink software and MATLAB Toolbox. The success rate of the SVM classifier is over 97%, which demonstrates the effectiveness and high efficiency of the developed method.

Training Classifiers with Shadow Features for Sensor-Based Human Activity Recognition

PubMed Central

Fong, Simon; Song, Wei; Cho, Kyungeun; Wong, Raymond; Wong, Kelvin K. L.

2017-01-01

In this paper, a novel training/testing process for building/using a classification model based on human activity recognition (HAR) is proposed. Traditionally, HAR has been accomplished by a classifier that learns the activities of a person by training with skeletal data obtained from a motion sensor, such as Microsoft Kinect. These skeletal data are the spatial coordinates (x, y, z) of different parts of the human body. The numeric information forms time series, temporal records of movement sequences that can be used for training a classifier. In addition to the spatial features that describe current positions in the skeletal data, new features called ‘shadow features’ are used to improve the supervised learning efficacy of the classifier. Shadow features are inferred from the dynamics of body movements, and thereby modelling the underlying momentum of the performed activities. They provide extra dimensions of information for characterising activities in the classification process, and thereby significantly improve the classification accuracy. Two cases of HAR are tested using a classification model trained with shadow features: one is by using wearable sensor and the other is by a Kinect-based remote sensor. Our experiments can demonstrate the advantages of the new method, which will have an impact on human activity detection research. PMID:28264470

Thermography based diagnosis of ruptured anterior cruciate ligament (ACL) in canines

NASA Astrophysics Data System (ADS)

Lama, Norsang; Umbaugh, Scott E.; Mishra, Deependra; Dahal, Rohini; Marino, Dominic J.; Sackman, Joseph

2016-09-01

Anterior cruciate ligament (ACL) rupture in canines is a common orthopedic injury in veterinary medicine. Veterinarians use both imaging and non-imaging methods to diagnose the disease. Common imaging methods such as radiography, computed tomography (CT scan) and magnetic resonance imaging (MRI) have some disadvantages: expensive setup, high dose of radiation, and time-consuming. In this paper, we present an alternative diagnostic method based on feature extraction and pattern classification (FEPC) to diagnose abnormal patterns in ACL thermograms. The proposed method was experimented with a total of 30 thermograms for each camera view (anterior, lateral and posterior) including 14 disease and 16 non-disease cases provided from Long Island Veterinary Specialists. The normal and abnormal patterns in thermograms are analyzed in two steps: feature extraction and pattern classification. Texture features based on gray level co-occurrence matrices (GLCM), histogram features and spectral features are extracted from the color normalized thermograms and the computed feature vectors are applied to Nearest Neighbor (NN) classifier, K-Nearest Neighbor (KNN) classifier and Support Vector Machine (SVM) classifier with leave-one-out validation method. The algorithm gives the best classification success rate of 86.67% with a sensitivity of 85.71% and a specificity of 87.5% in ACL rupture detection using NN classifier for the lateral view and Norm-RGB-Lum color normalization method. Our results show that the proposed method has the potential to detect ACL rupture in canines.

A target recognition method for maritime surveillance radars based on hybrid ensemble selection

NASA Astrophysics Data System (ADS)

Fan, Xueman; Hu, Shengliang; He, Jingbo

2017-11-01

In order to improve the generalisation ability of the maritime surveillance radar, a novel ensemble selection technique, termed Optimisation and Dynamic Selection (ODS), is proposed. During the optimisation phase, the non-dominated sorting genetic algorithm II for multi-objective optimisation is used to find the Pareto front, i.e. a set of ensembles of classifiers representing different tradeoffs between the classification error and diversity. During the dynamic selection phase, the meta-learning method is used to predict whether a candidate ensemble is competent enough to classify a query instance based on three different aspects, namely, feature space, decision space and the extent of consensus. The classification performance and time complexity of ODS are compared against nine other ensemble methods using a self-built full polarimetric high resolution range profile data-set. The experimental results clearly show the effectiveness of ODS. In addition, the influence of the selection of diversity measures is studied concurrently.

The Low Backscattering Objects Classification in Polsar Image Based on Bag of Words Model Using Support Vector Machine

NASA Astrophysics Data System (ADS)

Yang, L.; Shi, L.; Li, P.; Yang, J.; Zhao, L.; Zhao, B.

2018-04-01

Due to the forward scattering and block of radar signal, the water, bare soil, shadow, named low backscattering objects (LBOs), often present low backscattering intensity in polarimetric synthetic aperture radar (PolSAR) image. Because the LBOs rise similar backscattering intensity and polarimetric responses, the spectral-based classifiers are inefficient to deal with LBO classification, such as Wishart method. Although some polarimetric features had been exploited to relieve the confusion phenomenon, the backscattering features are still found unstable when the system noise floor varies in the range direction. This paper will introduce a simple but effective scene classification method based on Bag of Words (BoW) model using Support Vector Machine (SVM) to discriminate the LBOs, without relying on any polarimetric features. In the proposed approach, square windows are firstly opened around the LBOs adaptively to determine the scene images, and then the Scale-Invariant Feature Transform (SIFT) points are detected in training and test scenes. The several SIFT features detected are clustered using K-means to obtain certain cluster centers as the visual word lists and scene images are represented using word frequency. At last, the SVM is selected for training and predicting new scenes as some kind of LBOs. The proposed method is executed over two AIRSAR data sets at C band and L band, including water, bare soil and shadow scenes. The experimental results illustrate the effectiveness of the scene method in distinguishing LBOs.

Correlation pattern recognition: optimal parameters for quality standards control of chocolate marshmallow candy

NASA Astrophysics Data System (ADS)

Flores, Jorge L.; García-Torales, G.; Ponce Ávila, Cristina

2006-08-01

This paper describes an in situ image recognition system designed to inspect the quality standards of the chocolate pops during their production. The essence of the recognition system is the localization of the events (i.e., defects) in the input images that affect the quality standards of pops. To this end, processing modules, based on correlation filter, and segmentation of images are employed with the objective of measuring the quality standards. Therefore, we designed the correlation filter and defined a set of features from the correlation plane. The desired values for these parameters are obtained by exploiting information about objects to be rejected in order to find the optimal discrimination capability of the system. Regarding this set of features, the pop can be correctly classified. The efficacy of the system has been tested thoroughly under laboratory conditions using at least 50 images, containing 3 different types of possible defects.

Classifier ensemble based on feature selection and diversity measures for predicting the affinity of A(2B) adenosine receptor antagonists.

PubMed

Bonet, Isis; Franco-Montero, Pedro; Rivero, Virginia; Teijeira, Marta; Borges, Fernanda; Uriarte, Eugenio; Morales Helguera, Aliuska

2013-12-23

A(2B) adenosine receptor antagonists may be beneficial in treating diseases like asthma, diabetes, diabetic retinopathy, and certain cancers. This has stimulated research for the development of potent ligands for this subtype, based on quantitative structure-affinity relationships. In this work, a new ensemble machine learning algorithm is proposed for classification and prediction of the ligand-binding affinity of A(2B) adenosine receptor antagonists. This algorithm is based on the training of different classifier models with multiple training sets (composed of the same compounds but represented by diverse features). The k-nearest neighbor, decision trees, neural networks, and support vector machines were used as single classifiers. To select the base classifiers for combining into the ensemble, several diversity measures were employed. The final multiclassifier prediction results were computed from the output obtained by using a combination of selected base classifiers output, by utilizing different mathematical functions including the following: majority vote, maximum and average probability. In this work, 10-fold cross- and external validation were used. The strategy led to the following results: i) the single classifiers, together with previous features selections, resulted in good overall accuracy, ii) a comparison between single classifiers, and their combinations in the multiclassifier model, showed that using our ensemble gave a better performance than the single classifier model, and iii) our multiclassifier model performed better than the most widely used multiclassifier models in the literature. The results and statistical analysis demonstrated the supremacy of our multiclassifier approach for predicting the affinity of A(2B) adenosine receptor antagonists, and it can be used to develop other QSAR models.

Prostate tissue characterization/classification in 144 patient population using wavelet and higher order spectra features from transrectal ultrasound images.

PubMed

Pareek, Gyan; Acharya, U Rajendra; Sree, S Vinitha; Swapna, G; Yantri, Ratna; Martis, Roshan Joy; Saba, Luca; Krishnamurthi, Ganapathy; Mallarini, Giorgio; El-Baz, Ayman; Al Ekish, Shadi; Beland, Michael; Suri, Jasjit S

2013-12-01

In this work, we have proposed an on-line computer-aided diagnostic system called "UroImage" that classifies a Transrectal Ultrasound (TRUS) image into cancerous or non-cancerous with the help of non-linear Higher Order Spectra (HOS) features and Discrete Wavelet Transform (DWT) coefficients. The UroImage system consists of an on-line system where five significant features (one DWT-based feature and four HOS-based features) are extracted from the test image. These on-line features are transformed by the classifier parameters obtained using the training dataset to determine the class. We trained and tested six classifiers. The dataset used for evaluation had 144 TRUS images which were split into training and testing sets. Three-fold and ten-fold cross-validation protocols were adopted for training and estimating the accuracy of the classifiers. The ground truth used for training was obtained using the biopsy results. Among the six classifiers, using 10-fold cross-validation technique, Support Vector Machine and Fuzzy Sugeno classifiers presented the best classification accuracy of 97.9% with equally high values for sensitivity, specificity and positive predictive value. Our proposed automated system, which achieved more than 95% values for all the performance measures, can be an adjunct tool to provide an initial diagnosis for the identification of patients with prostate cancer. The technique, however, is limited by the limitations of 2D ultrasound guided biopsy, and we intend to improve our technique by using 3D TRUS images in the future.

Area Determination of Diabetic Foot Ulcer Images Using a Cascaded Two-Stage SVM-Based Classification.

PubMed

Wang, Lei; Pedersen, Peder C; Agu, Emmanuel; Strong, Diane M; Tulu, Bengisu

2017-09-01

The standard chronic wound assessment method based on visual examination is potentially inaccurate and also represents a significant clinical workload. Hence, computer-based systems providing quantitative wound assessment may be valuable for accurately monitoring wound healing status, with the wound area the best suited for automated analysis. Here, we present a novel approach, using support vector machines (SVM) to determine the wound boundaries on foot ulcer images captured with an image capture box, which provides controlled lighting and range. After superpixel segmentation, a cascaded two-stage classifier operates as follows: in the first stage, a set of k binary SVM classifiers are trained and applied to different subsets of the entire training images dataset, and incorrectly classified instances are collected. In the second stage, another binary SVM classifier is trained on the incorrectly classified set. We extracted various color and texture descriptors from superpixels that are used as input for each stage in the classifier training. Specifically, color and bag-of-word representations of local dense scale invariant feature transformation features are descriptors for ruling out irrelevant regions, and color and wavelet-based features are descriptors for distinguishing healthy tissue from wound regions. Finally, the detected wound boundary is refined by applying the conditional random field method. We have implemented the wound classification on a Nexus 5 smartphone platform, except for training which was done offline. Results are compared with other classifiers and show that our approach provides high global performance rates (average sensitivity = 73.3%, specificity = 94.6%) and is sufficiently efficient for a smartphone-based image analysis.

Objective measurement of erythema in psoriasis using digital color photography with color calibration.

PubMed

Raina, A; Hennessy, R; Rains, M; Allred, J; Hirshburg, J M; Diven, D G; Markey, M K

2016-08-01

Traditional metrics for evaluating the severity of psoriasis are subjective, which complicates efforts to measure effective treatments in clinical trials. We collected images of psoriasis plaques and calibrated the coloration of the images according to an included color card. Features were extracted from the images and used to train a linear discriminant analysis classifier with cross-validation to automatically classify the degree of erythema. The results were tested against numerical scores obtained by a panel of dermatologists using a standard rating system. Quantitative measures of erythema based on the digital color images showed good agreement with subjective assessment of erythema severity (κ = 0.4203). The color calibration process improved the agreement from κ = 0.2364 to κ = 0.4203. We propose a method for the objective measurement of the psoriasis severity parameter of erythema and show that the calibration process improved the results. © 2015 John Wiley & Sons A/S. Published by John Wiley & Sons Ltd.

Differential diagnosis of CT focal liver lesions using texture features, feature selection and ensemble driven classifiers.

PubMed

Mougiakakou, Stavroula G; Valavanis, Ioannis K; Nikita, Alexandra; Nikita, Konstantina S

2007-09-01

The aim of the present study is to define an optimally performing computer-aided diagnosis (CAD) architecture for the classification of liver tissue from non-enhanced computed tomography (CT) images into normal liver (C1), hepatic cyst (C2), hemangioma (C3), and hepatocellular carcinoma (C4). To this end, various CAD architectures, based on texture features and ensembles of classifiers (ECs), are comparatively assessed. Number of regions of interests (ROIs) corresponding to C1-C4 have been defined by experienced radiologists in non-enhanced liver CT images. For each ROI, five distinct sets of texture features were extracted using first order statistics, spatial gray level dependence matrix, gray level difference method, Laws' texture energy measures, and fractal dimension measurements. Two different ECs were constructed and compared. The first one consists of five multilayer perceptron neural networks (NNs), each using as input one of the computed texture feature sets or its reduced version after genetic algorithm-based feature selection. The second EC comprised five different primary classifiers, namely one multilayer perceptron NN, one probabilistic NN, and three k-nearest neighbor classifiers, each fed with the combination of the five texture feature sets or their reduced versions. The final decision of each EC was extracted by using appropriate voting schemes, while bootstrap re-sampling was utilized in order to estimate the generalization ability of the CAD architectures based on the available relatively small-sized data set. The best mean classification accuracy (84.96%) is achieved by the second EC using a fused feature set, and the weighted voting scheme. The fused feature set was obtained after appropriate feature selection applied to specific subsets of the original feature set. The comparative assessment of the various CAD architectures shows that combining three types of classifiers with a voting scheme, fed with identical feature sets obtained after appropriate feature selection and fusion, may result in an accurate system able to assist differential diagnosis of focal liver lesions from non-enhanced CT images.

Classifier Subset Selection for the Stacked Generalization Method Applied to Emotion Recognition in Speech

PubMed Central

Álvarez, Aitor; Sierra, Basilio; Arruti, Andoni; López-Gil, Juan-Miguel; Garay-Vitoria, Nestor

2015-01-01

In this paper, a new supervised classification paradigm, called classifier subset selection for stacked generalization (CSS stacking), is presented to deal with speech emotion recognition. The new approach consists of an improvement of a bi-level multi-classifier system known as stacking generalization by means of an integration of an estimation of distribution algorithm (EDA) in the first layer to select the optimal subset from the standard base classifiers. The good performance of the proposed new paradigm was demonstrated over different configurations and datasets. First, several CSS stacking classifiers were constructed on the RekEmozio dataset, using some specific standard base classifiers and a total of 123 spectral, quality and prosodic features computed using in-house feature extraction algorithms. These initial CSS stacking classifiers were compared to other multi-classifier systems and the employed standard classifiers built on the same set of speech features. Then, new CSS stacking classifiers were built on RekEmozio using a different set of both acoustic parameters (extended version of the Geneva Minimalistic Acoustic Parameter Set (eGeMAPS)) and standard classifiers and employing the best meta-classifier of the initial experiments. The performance of these two CSS stacking classifiers was evaluated and compared. Finally, the new paradigm was tested on the well-known Berlin Emotional Speech database. We compared the performance of single, standard stacking and CSS stacking systems using the same parametrization of the second phase. All of the classifications were performed at the categorical level, including the six primary emotions plus the neutral one. PMID:26712757

Recognition of emotions using multimodal physiological signals and an ensemble deep learning model.

PubMed

Yin, Zhong; Zhao, Mengyuan; Wang, Yongxiong; Yang, Jingdong; Zhang, Jianhua

2017-03-01

Using deep-learning methodologies to analyze multimodal physiological signals becomes increasingly attractive for recognizing human emotions. However, the conventional deep emotion classifiers may suffer from the drawback of the lack of the expertise for determining model structure and the oversimplification of combining multimodal feature abstractions. In this study, a multiple-fusion-layer based ensemble classifier of stacked autoencoder (MESAE) is proposed for recognizing emotions, in which the deep structure is identified based on a physiological-data-driven approach. Each SAE consists of three hidden layers to filter the unwanted noise in the physiological features and derives the stable feature representations. An additional deep model is used to achieve the SAE ensembles. The physiological features are split into several subsets according to different feature extraction approaches with each subset separately encoded by a SAE. The derived SAE abstractions are combined according to the physiological modality to create six sets of encodings, which are then fed to a three-layer, adjacent-graph-based network for feature fusion. The fused features are used to recognize binary arousal or valence states. DEAP multimodal database was employed to validate the performance of the MESAE. By comparing with the best existing emotion classifier, the mean of classification rate and F-score improves by 5.26%. The superiority of the MESAE against the state-of-the-art shallow and deep emotion classifiers has been demonstrated under different sizes of the available physiological instances. Copyright © 2016 Elsevier Ireland Ltd. All rights reserved.

Semantic classification of urban buildings combining VHR image and GIS data: An improved random forest approach

NASA Astrophysics Data System (ADS)

Du, Shihong; Zhang, Fangli; Zhang, Xiuyuan

2015-07-01

While most existing studies have focused on extracting geometric information on buildings, only a few have concentrated on semantic information. The lack of semantic information cannot satisfy many demands on resolving environmental and social issues. This study presents an approach to semantically classify buildings into much finer categories than those of existing studies by learning random forest (RF) classifier from a large number of imbalanced samples with high-dimensional features. First, a two-level segmentation mechanism combining GIS and VHR image produces single image objects at a large scale and intra-object components at a small scale. Second, a semi-supervised method chooses a large number of unbiased samples by considering the spatial proximity and intra-cluster similarity of buildings. Third, two important improvements in RF classifier are made: a voting-distribution ranked rule for reducing the influences of imbalanced samples on classification accuracy and a feature importance measurement for evaluating each feature's contribution to the recognition of each category. Fourth, the semantic classification of urban buildings is practically conducted in Beijing city, and the results demonstrate that the proposed approach is effective and accurate. The seven categories used in the study are finer than those in existing work and more helpful to studying many environmental and social problems.

Objectively classifying Southern Hemisphere extratropical cyclones

NASA Astrophysics Data System (ADS)

Catto, Jennifer

2016-04-01

There has been a long tradition in attempting to separate extratropical cyclones into different classes depending on their cloud signatures, airflows, synoptic precursors, or upper-level flow features. Depending on these features, the cyclones may have different impacts, for example in their precipitation intensity. It is important, therefore, to understand how the distribution of different cyclone classes may change in the future. Many of the previous classifications have been performed manually. In order to be able to evaluate climate models and understand how extratropical cyclones might change in the future, we need to be able to use an automated method to classify cyclones. Extratropical cyclones have been identified in the Southern Hemisphere from the ERA-Interim reanalysis dataset with a commonly used identification and tracking algorithm that employs 850 hPa relative vorticity. A clustering method applied to large-scale fields from ERA-Interim at the time of cyclone genesis (when the cyclone is first detected), has been used to objectively classify identified cyclones. The results are compared to the manual classification of Sinclair and Revell (2000) and the four objectively identified classes shown in this presentation are found to match well. The relative importance of diabatic heating in the clusters is investigated, as well as the differing precipitation characteristics. The success of the objective classification shows its utility in climate model evaluation and climate change studies.

Kruskal-Wallis-based computationally efficient feature selection for face recognition.

PubMed

Ali Khan, Sajid; Hussain, Ayyaz; Basit, Abdul; Akram, Sheeraz

2014-01-01

Face recognition in today's technological world, and face recognition applications attain much more importance. Most of the existing work used frontal face images to classify face image. However these techniques fail when applied on real world face images. The proposed technique effectively extracts the prominent facial features. Most of the features are redundant and do not contribute to representing face. In order to eliminate those redundant features, computationally efficient algorithm is used to select the more discriminative face features. Extracted features are then passed to classification step. In the classification step, different classifiers are ensemble to enhance the recognition accuracy rate as single classifier is unable to achieve the high accuracy. Experiments are performed on standard face database images and results are compared with existing techniques.

Classifying Physical Morphology of Cocoa Beans Digital Images using Multiclass Ensemble Least-Squares Support Vector Machine

NASA Astrophysics Data System (ADS)

Lawi, Armin; Adhitya, Yudhi

2018-03-01

The objective of this research is to determine the quality of cocoa beans through morphology of their digital images. Samples of cocoa beans were scattered on a bright white paper under a controlled lighting condition. A compact digital camera was used to capture the images. The images were then processed to extract their morphological parameters. Classification process begins with an analysis of cocoa beans image based on morphological feature extraction. Parameters for extraction of morphological or physical feature parameters, i.e., Area, Perimeter, Major Axis Length, Minor Axis Length, Aspect Ratio, Circularity, Roundness, Ferret Diameter. The cocoa beans are classified into 4 groups, i.e.: Normal Beans, Broken Beans, Fractured Beans, and Skin Damaged Beans. The model of classification used in this paper is the Multiclass Ensemble Least-Squares Support Vector Machine (MELS-SVM), a proposed improvement model of SVM using ensemble method in which the separate hyperplanes are obtained by least square approach and the multiclass procedure uses One-Against- All method. The result of our proposed model showed that the classification with morphological feature input parameters were accurately as 99.705% for the four classes, respectively.

Quantitative CT analysis for the preoperative prediction of pathologic grade in pancreatic neuroendocrine tumors

NASA Astrophysics Data System (ADS)

Chakraborty, Jayasree; Pulvirenti, Alessandra; Yamashita, Rikiya; Midya, Abhishek; Gönen, Mithat; Klimstra, David S.; Reidy, Diane L.; Allen, Peter J.; Do, Richard K. G.; Simpson, Amber L.

2018-02-01

Pancreatic neuroendocrine tumors (PanNETs) account for approximately 5% of all pancreatic tumors, affecting one individual per million each year.1 PanNETs are difficult to treat due to biological variability from benign to highly malignant, indolent to very aggressive. The World Health Organization classifies PanNETs into three categories based on cell proliferative rate, usually detected using the Ki67 index and cell morphology: low-grade (G1), intermediate-grade (G2) and high-grade (G3) tumors. Knowledge of grade prior to treatment would select patients for optimal therapy: G1/G2 tumors respond well to somatostatin analogs and targeted or cytotoxic drugs whereas G3 tumors would be targeted with platinum or alkylating agents.2, 3 Grade assessment is based on the pathologic examination of the surgical specimen, biopsy or ne-needle aspiration; however, heterogeneity in the proliferative index can lead to sampling errors.4 Based on studies relating qualitatively assessed shape and enhancement characteristics on CT imaging to tumor grade in PanNET,5 we propose objective classification of PanNET grade with quantitative analysis of CT images. Fifty-five patients were included in our retrospective analysis. A pathologist graded the tumors. Texture and shape-based features were extracted from CT. Random forest and naive Bayes classifiers were compared for the classification of G1/G2 and G3 PanNETs. The best area under the receiver operating characteristic curve (AUC) of 0:74 and accuracy of 71:64% was achieved with texture features. The shape-based features achieved an AUC of 0:70 and accuracy of 78:73%.

Diagnosis of the OCD Patients using Drawing Features of the Bender Gestalt Shapes.

PubMed

Boostani, R; Asadi, F; Mohammadi, N

2017-03-01

Since psychological tests such as questionnaire or drawing tests are almost qualitative, their results carry a degree of uncertainty and sometimes subjectivity. The deficiency of all drawing tests is that the assessment is carried out after drawing the objects and lots of information such as pen angle, speed, curvature and pressure are missed through the test. In other words, the psychologists cannot assess their patients while running the tests. One of the famous drawing tests to measure the degree of Obsession Compulsion Disorder (OCD) is the Bender Gestalt, though its reliability is not promising. The main objective of this study is to make the Bender Gestalt test quantitative; therefore, an optical pen along with a digital tablet is utilized to preserve the key drawing features of OCD patients during the test. Among a large population of patients who referred to a special clinic of OCD, 50 under therapy subjects voluntarily took part in this study. In contrast, 50 subjects with no sign of OCD performed the test as a control group. This test contains 9 shapes and the participants were not constraint to draw the shapes in a certain interval of time; consequently, to classify the stream of feature vectors (samples through drawing) Hidden Markov Model (HMM) is employed and its flexibility increased by incorporating the fuzzy technique into its learning scheme. Applying fuzzy HMM classifier to the data stream of subjects could classify two groups up to 95.2% accuracy, whereas the results by applying the standard HMM resulted in 94.5%. In addition, multi-layer perceptron (MLP), as a strong static classifier, is applied to the features and resulted in 86.6% accuracy. Applying the pair of T-test to the results implies a significant supremacy of the fuzzy HMM to the standard HMM and MLP classifiers.

Arrhythmia Classification Based on Multi-Domain Feature Extraction for an ECG Recognition System.

PubMed

Li, Hongqiang; Yuan, Danyang; Wang, Youxi; Cui, Dianyin; Cao, Lu

2016-10-20

Automatic recognition of arrhythmias is particularly important in the diagnosis of heart diseases. This study presents an electrocardiogram (ECG) recognition system based on multi-domain feature extraction to classify ECG beats. An improved wavelet threshold method for ECG signal pre-processing is applied to remove noise interference. A novel multi-domain feature extraction method is proposed; this method employs kernel-independent component analysis in nonlinear feature extraction and uses discrete wavelet transform to extract frequency domain features. The proposed system utilises a support vector machine classifier optimized with a genetic algorithm to recognize different types of heartbeats. An ECG acquisition experimental platform, in which ECG beats are collected as ECG data for classification, is constructed to demonstrate the effectiveness of the system in ECG beat classification. The presented system, when applied to the MIT-BIH arrhythmia database, achieves a high classification accuracy of 98.8%. Experimental results based on the ECG acquisition experimental platform show that the system obtains a satisfactory classification accuracy of 97.3% and is able to classify ECG beats efficiently for the automatic identification of cardiac arrhythmias.

Arrhythmia Classification Based on Multi-Domain Feature Extraction for an ECG Recognition System

PubMed Central

Li, Hongqiang; Yuan, Danyang; Wang, Youxi; Cui, Dianyin; Cao, Lu

2016-01-01

Automatic recognition of arrhythmias is particularly important in the diagnosis of heart diseases. This study presents an electrocardiogram (ECG) recognition system based on multi-domain feature extraction to classify ECG beats. An improved wavelet threshold method for ECG signal pre-processing is applied to remove noise interference. A novel multi-domain feature extraction method is proposed; this method employs kernel-independent component analysis in nonlinear feature extraction and uses discrete wavelet transform to extract frequency domain features. The proposed system utilises a support vector machine classifier optimized with a genetic algorithm to recognize different types of heartbeats. An ECG acquisition experimental platform, in which ECG beats are collected as ECG data for classification, is constructed to demonstrate the effectiveness of the system in ECG beat classification. The presented system, when applied to the MIT-BIH arrhythmia database, achieves a high classification accuracy of 98.8%. Experimental results based on the ECG acquisition experimental platform show that the system obtains a satisfactory classification accuracy of 97.3% and is able to classify ECG beats efficiently for the automatic identification of cardiac arrhythmias. PMID:27775596

Tree Species Classification of Broadleaved Forests in Nagano, Central Japan, Using Airborne Laser Data and Multispectral Images

NASA Astrophysics Data System (ADS)

Deng, S.; Katoh, M.; Takenaka, Y.; Cheung, K.; Ishii, A.; Fujii, N.; Gao, T.

2017-10-01

This study attempted to classify three coniferous and ten broadleaved tree species by combining airborne laser scanning (ALS) data and multispectral images. The study area, located in Nagano, central Japan, is within the broadleaved forests of the Afan Woodland area. A total of 235 trees were surveyed in 2016, and we recorded the species, DBH, and tree height. The geographical position of each tree was collected using a Global Navigation Satellite System (GNSS) device. Tree crowns were manually detected using GNSS position data, field photographs, true-color orthoimages with three bands (red-green-blue, RGB), 3D point clouds, and a canopy height model derived from ALS data. Then a total of 69 features, including 27 image-based and 42 point-based features, were extracted from the RGB images and the ALS data to classify tree species. Finally, the detected tree crowns were classified into two classes for the first level (coniferous and broadleaved trees), four classes for the second level (Pinus densiflora, Larix kaempferi, Cryptomeria japonica, and broadleaved trees), and 13 classes for the third level (three coniferous and ten broadleaved species), using the 27 image-based features, 42 point-based features, all 69 features, and the best combination of features identified using a neighborhood component analysis algorithm, respectively. The overall classification accuracies reached 90 % at the first and second levels but less than 60 % at the third level. The classifications using the best combinations of features had higher accuracies than those using the image-based and point-based features and the combination of all of the 69 features.

Progressively expanded neural network for automatic material identification in hyperspectral imagery

NASA Astrophysics Data System (ADS)

Paheding, Sidike

The science of hyperspectral remote sensing focuses on the exploitation of the spectral signatures of various materials to enhance capabilities including object detection, recognition, and material characterization. Hyperspectral imagery (HSI) has been extensively used for object detection and identification applications since it provides plenty of spectral information to uniquely identify materials by their reflectance spectra. HSI-based object detection algorithms can be generally classified into stochastic and deterministic approaches. Deterministic approaches are comparatively simple to apply since it is usually based on direct spectral similarity such as spectral angles or spectral correlation. In contrast, stochastic algorithms require statistical modeling and estimation for target class and non-target class. Over the decades, many single class object detection methods have been proposed in the literature, however, deterministic multiclass object detection in HSI has not been explored. In this work, we propose a deterministic multiclass object detection scheme, named class-associative spectral fringe-adjusted joint transform correlation. Human brain is capable of simultaneously processing high volumes of multi-modal data received every second of the day. In contrast, a machine sees input data simply as random binary numbers. Although machines are computationally efficient, they are inferior when comes to data abstraction and interpretation. Thus, mimicking the learning strength of human brain has been current trend in artificial intelligence. In this work, we present a biological inspired neural network, named progressively expanded neural network (PEN Net), based on nonlinear transformation of input neurons to a feature space for better pattern differentiation. In PEN Net, discrete fixed excitations are disassembled and scattered in the feature space as a nonlinear line. Each disassembled element on the line corresponds to a pattern with similar features. Unlike the conventional neural network where hidden neurons need to be iteratively adjusted to achieve better accuracy, our proposed PEN Net does not require hidden neurons tuning which achieves better computational efficiency, and it has also shown superior performance in HSI classification tasks compared to the state-of-the-arts. Spectral-spatial features based HSI classification framework has shown stronger strength compared to spectral-only based methods. In our lastly proposed technique, PEN Net is incorporated with multiscale spatial features (i.e., multiscale complete local binary pattern) to perform a spectral-spatial classification of HSI. Several experiments demonstrate excellent performance of our proposed technique compared to the more recent developed approaches.

DOE Office of Scientific and Technical Information (OSTI.GOV)

Aghaei, Faranak; Tan, Maxine; Liu, Hong

Purpose: To identify a new clinical marker based on quantitative kinetic image features analysis and assess its feasibility to predict tumor response to neoadjuvant chemotherapy. Methods: The authors assembled a dataset involving breast MR images acquired from 68 cancer patients before undergoing neoadjuvant chemotherapy. Among them, 25 patients had complete response (CR) and 43 had partial and nonresponse (NR) to chemotherapy based on the response evaluation criteria in solid tumors. The authors developed a computer-aided detection scheme to segment breast areas and tumors depicted on the breast MR images and computed a total of 39 kinetic image features from bothmore » tumor and background parenchymal enhancement regions. The authors then applied and tested two approaches to classify between CR and NR cases. The first one analyzed each individual feature and applied a simple feature fusion method that combines classification results from multiple features. The second approach tested an attribute selected classifier that integrates an artificial neural network (ANN) with a wrapper subset evaluator, which was optimized using a leave-one-case-out validation method. Results: In the pool of 39 features, 10 yielded relatively higher classification performance with the areas under receiver operating characteristic curves (AUCs) ranging from 0.61 to 0.78 to classify between CR and NR cases. Using a feature fusion method, the maximum AUC = 0.85 ± 0.05. Using the ANN-based classifier, AUC value significantly increased to 0.96 ± 0.03 (p < 0.01). Conclusions: This study demonstrated that quantitative analysis of kinetic image features computed from breast MR images acquired prechemotherapy has potential to generate a useful clinical marker in predicting tumor response to chemotherapy.« less

Computer vision-based method for classification of wheat grains using artificial neural network.

PubMed

Sabanci, Kadir; Kayabasi, Ahmet; Toktas, Abdurrahim

2017-06-01

A simplified computer vision-based application using artificial neural network (ANN) depending on multilayer perceptron (MLP) for accurately classifying wheat grains into bread or durum is presented. The images of 100 bread and 100 durum wheat grains are taken via a high-resolution camera and subjected to pre-processing. The main visual features of four dimensions, three colors and five textures are acquired using image-processing techniques (IPTs). A total of 21 visual features are reproduced from the 12 main features to diversify the input population for training and testing the ANN model. The data sets of visual features are considered as input parameters of the ANN model. The ANN with four different input data subsets is modelled to classify the wheat grains into bread or durum. The ANN model is trained with 180 grains and its accuracy tested with 20 grains from a total of 200 wheat grains. Seven input parameters that are most effective on the classifying results are determined using the correlation-based CfsSubsetEval algorithm to simplify the ANN model. The results of the ANN model are compared in terms of accuracy rate. The best result is achieved with a mean absolute error (MAE) of 9.8 × 10 -6 by the simplified ANN model. This shows that the proposed classifier based on computer vision can be successfully exploited to automatically classify a variety of grains. © 2016 Society of Chemical Industry. © 2016 Society of Chemical Industry.

Automatic migraine classification via feature selection committee and machine learning techniques over imaging and questionnaire data.

PubMed

Garcia-Chimeno, Yolanda; Garcia-Zapirain, Begonya; Gomez-Beldarrain, Marian; Fernandez-Ruanova, Begonya; Garcia-Monco, Juan Carlos

2017-04-13

Feature selection methods are commonly used to identify subsets of relevant features to facilitate the construction of models for classification, yet little is known about how feature selection methods perform in diffusion tensor images (DTIs). In this study, feature selection and machine learning classification methods were tested for the purpose of automating diagnosis of migraines using both DTIs and questionnaire answers related to emotion and cognition - factors that influence of pain perceptions. We select 52 adult subjects for the study divided into three groups: control group (15), subjects with sporadic migraine (19) and subjects with chronic migraine and medication overuse (18). These subjects underwent magnetic resonance with diffusion tensor to see white matter pathway integrity of the regions of interest involved in pain and emotion. The tests also gather data about pathology. The DTI images and test results were then introduced into feature selection algorithms (Gradient Tree Boosting, L1-based, Random Forest and Univariate) to reduce features of the first dataset and classification algorithms (SVM (Support Vector Machine), Boosting (Adaboost) and Naive Bayes) to perform a classification of migraine group. Moreover we implement a committee method to improve the classification accuracy based on feature selection algorithms. When classifying the migraine group, the greatest improvements in accuracy were made using the proposed committee-based feature selection method. Using this approach, the accuracy of classification into three types improved from 67 to 93% when using the Naive Bayes classifier, from 90 to 95% with the support vector machine classifier, 93 to 94% in boosting. The features that were determined to be most useful for classification included are related with the pain, analgesics and left uncinate brain (connected with the pain and emotions). The proposed feature selection committee method improved the performance of migraine diagnosis classifiers compared to individual feature selection methods, producing a robust system that achieved over 90% accuracy in all classifiers. The results suggest that the proposed methods can be used to support specialists in the classification of migraines in patients undergoing magnetic resonance imaging.

An Exemplar-Based Multi-View Domain Generalization Framework for Visual Recognition.

PubMed

Niu, Li; Li, Wen; Xu, Dong; Cai, Jianfei

2018-02-01

In this paper, we propose a new exemplar-based multi-view domain generalization (EMVDG) framework for visual recognition by learning robust classifier that are able to generalize well to arbitrary target domain based on the training samples with multiple types of features (i.e., multi-view features). In this framework, we aim to address two issues simultaneously. First, the distribution of training samples (i.e., the source domain) is often considerably different from that of testing samples (i.e., the target domain), so the performance of the classifiers learnt on the source domain may drop significantly on the target domain. Moreover, the testing data are often unseen during the training procedure. Second, when the training data are associated with multi-view features, the recognition performance can be further improved by exploiting the relation among multiple types of features. To address the first issue, considering that it has been shown that fusing multiple SVM classifiers can enhance the domain generalization ability, we build our EMVDG framework upon exemplar SVMs (ESVMs), in which a set of ESVM classifiers are learnt with each one trained based on one positive training sample and all the negative training samples. When the source domain contains multiple latent domains, the learnt ESVM classifiers are expected to be grouped into multiple clusters. To address the second issue, we propose two approaches under the EMVDG framework based on the consensus principle and the complementary principle, respectively. Specifically, we propose an EMVDG_CO method by adding a co-regularizer to enforce the cluster structures of ESVM classifiers on different views to be consistent based on the consensus principle. Inspired by multiple kernel learning, we also propose another EMVDG_MK method by fusing the ESVM classifiers from different views based on the complementary principle. In addition, we further extend our EMVDG framework to exemplar-based multi-view domain adaptation (EMVDA) framework when the unlabeled target domain data are available during the training procedure. The effectiveness of our EMVDG and EMVDA frameworks for visual recognition is clearly demonstrated by comprehensive experiments on three benchmark data sets.

Age and gender estimation using Region-SIFT and multi-layered SVM

NASA Astrophysics Data System (ADS)

Kim, Hyunduk; Lee, Sang-Heon; Sohn, Myoung-Kyu; Hwang, Byunghun

2018-04-01

In this paper, we propose an age and gender estimation framework using the region-SIFT feature and multi-layered SVM classifier. The suggested framework entails three processes. The first step is landmark based face alignment. The second step is the feature extraction step. In this step, we introduce the region-SIFT feature extraction method based on facial landmarks. First, we define sub-regions of the face. We then extract SIFT features from each sub-region. In order to reduce the dimensions of features we employ a Principal Component Analysis (PCA) and a Linear Discriminant Analysis (LDA). Finally, we classify age and gender using a multi-layered Support Vector Machines (SVM) for efficient classification. Rather than performing gender estimation and age estimation independently, the use of the multi-layered SVM can improve the classification rate by constructing a classifier that estimate the age according to gender. Moreover, we collect a dataset of face images, called by DGIST_C, from the internet. A performance evaluation of proposed method was performed with the FERET database, CACD database, and DGIST_C database. The experimental results demonstrate that the proposed approach classifies age and performs gender estimation very efficiently and accurately.

Context-based automated defect classification system using multiple morphological masks

DOEpatents

Gleason, Shaun S.; Hunt, Martin A.; Sari-Sarraf, Hamed

2002-01-01

Automatic detection of defects during the fabrication of semiconductor wafers is largely automated, but the classification of those defects is still performed manually by technicians. This invention includes novel digital image analysis techniques that generate unique feature vector descriptions of semiconductor defects as well as classifiers that use these descriptions to automatically categorize the defects into one of a set of pre-defined classes. Feature extraction techniques based on multiple-focus images, multiple-defect mask images, and segmented semiconductor wafer images are used to create unique feature-based descriptions of the semiconductor defects. These feature-based defect descriptions are subsequently classified by a defect classifier into categories that depend on defect characteristics and defect contextual information, that is, the semiconductor process layer(s) with which the defect comes in contact. At the heart of the system is a knowledge database that stores and distributes historical semiconductor wafer and defect data to guide the feature extraction and classification processes. In summary, this invention takes as its input a set of images containing semiconductor defect information, and generates as its output a classification for the defect that describes not only the defect itself, but also the location of that defect with respect to the semiconductor process layers.

Deep Convolutional Neural Networks for Classifying Body Constitution Based on Face Image.

PubMed

Huan, Er-Yang; Wen, Gui-Hua; Zhang, Shi-Jun; Li, Dan-Yang; Hu, Yang; Chang, Tian-Yuan; Wang, Qing; Huang, Bing-Lin

2017-01-01

Body constitution classification is the basis and core content of traditional Chinese medicine constitution research. It is to extract the relevant laws from the complex constitution phenomenon and finally build the constitution classification system. Traditional identification methods have the disadvantages of inefficiency and low accuracy, for instance, questionnaires. This paper proposed a body constitution recognition algorithm based on deep convolutional neural network, which can classify individual constitution types according to face images. The proposed model first uses the convolutional neural network to extract the features of face image and then combines the extracted features with the color features. Finally, the fusion features are input to the Softmax classifier to get the classification result. Different comparison experiments show that the algorithm proposed in this paper can achieve the accuracy of 65.29% about the constitution classification. And its performance was accepted by Chinese medicine practitioners.

Nonlinear features for classification and pose estimation of machined parts from single views

NASA Astrophysics Data System (ADS)

Talukder, Ashit; Casasent, David P.

1998-10-01

A new nonlinear feature extraction method is presented for classification and pose estimation of objects from single views. The feature extraction method is called the maximum representation and discrimination feature (MRDF) method. The nonlinear MRDF transformations to use are obtained in closed form, and offer significant advantages compared to nonlinear neural network implementations. The features extracted are useful for both object discrimination (classification) and object representation (pose estimation). We consider MRDFs on image data, provide a new 2-stage nonlinear MRDF solution, and show it specializes to well-known linear and nonlinear image processing transforms under certain conditions. We show the use of MRDF in estimating the class and pose of images of rendered solid CAD models of machine parts from single views using a feature-space trajectory neural network classifier. We show new results with better classification and pose estimation accuracy than are achieved by standard principal component analysis and Fukunaga-Koontz feature extraction methods.

Automatic Polyp Detection via A Novel Unified Bottom-up and Top-down Saliency Approach.

PubMed

Yuan, Yixuan; Li, Dengwang; Meng, Max Q-H

2017-07-31

In this paper, we propose a novel automatic computer-aided method to detect polyps for colonoscopy videos. To find the perceptually and semantically meaningful salient polyp regions, we first segment images into multilevel superpixels. Each level corresponds to different sizes of superpixels. Rather than adopting hand-designed features to describe these superpixels in images, we employ sparse autoencoder (SAE) to learn discriminative features in an unsupervised way. Then a novel unified bottom-up and top-down saliency method is proposed to detect polyps. In the first stage, we propose a weak bottom-up (WBU) saliency map by fusing the contrast based saliency and object-center based saliency together. The contrast based saliency map highlights image parts that show different appearances compared with surrounding areas while the object-center based saliency map emphasizes the center of the salient object. In the second stage, a strong classifier with Multiple Kernel Boosting (MKB) is learned to calculate the strong top-down (STD) saliency map based on samples directly from the obtained multi-level WBU saliency maps. We finally integrate these two stage saliency maps from all levels together to highlight polyps. Experiment results achieve 0.818 recall for saliency calculation, validating the effectiveness of our method. Extensive experiments on public polyp datasets demonstrate that the proposed saliency algorithm performs favorably against state-of-the-art saliency methods to detect polyps.

A Novel Feature Selection Technique for Text Classification Using Naïve Bayes.

PubMed

Dey Sarkar, Subhajit; Goswami, Saptarsi; Agarwal, Aman; Aktar, Javed

2014-01-01

With the proliferation of unstructured data, text classification or text categorization has found many applications in topic classification, sentiment analysis, authorship identification, spam detection, and so on. There are many classification algorithms available. Naïve Bayes remains one of the oldest and most popular classifiers. On one hand, implementation of naïve Bayes is simple and, on the other hand, this also requires fewer amounts of training data. From the literature review, it is found that naïve Bayes performs poorly compared to other classifiers in text classification. As a result, this makes the naïve Bayes classifier unusable in spite of the simplicity and intuitiveness of the model. In this paper, we propose a two-step feature selection method based on firstly a univariate feature selection and then feature clustering, where we use the univariate feature selection method to reduce the search space and then apply clustering to select relatively independent feature sets. We demonstrate the effectiveness of our method by a thorough evaluation and comparison over 13 datasets. The performance improvement thus achieved makes naïve Bayes comparable or superior to other classifiers. The proposed algorithm is shown to outperform other traditional methods like greedy search based wrapper or CFS.

Proposal for Classifying the Severity of Speech Disorder Using a Fuzzy Model in Accordance with the Implicational Model of Feature Complexity

ERIC Educational Resources Information Center

Brancalioni, Ana Rita; Magnago, Karine Faverzani; Keske-Soares, Marcia

2012-01-01

The objective of this study is to create a new proposal for classifying the severity of speech disorders using a fuzzy model in accordance with a linguistic model that represents the speech acquisition of Brazilian Portuguese. The fuzzy linguistic model was run in the MATLAB software fuzzy toolbox from a set of fuzzy rules, and it encompassed…

Classification of urban features using airborne hyperspectral data

NASA Astrophysics Data System (ADS)

Ganesh Babu, Bharath

Accurate mapping and modeling of urban environments are critical for their efficient and successful management. Superior understanding of complex urban environments is made possible by using modern geospatial technologies. This research focuses on thematic classification of urban land use and land cover (LULC) using 248 bands of 2.0 meter resolution hyperspectral data acquired from an airborne imaging spectrometer (AISA+) on 24th July 2006 in and near Terre Haute, Indiana. Three distinct study areas including two commercial classes, two residential classes, and two urban parks/recreational classes were selected for classification and analysis. Four commonly used classification methods -- maximum likelihood (ML), extraction and classification of homogeneous objects (ECHO), spectral angle mapper (SAM), and iterative self organizing data analysis (ISODATA) - were applied to each data set. Accuracy assessment was conducted and overall accuracies were compared between the twenty four resulting thematic maps. With the exception of SAM and ISODATA in a complex commercial area, all methods employed classified the designated urban features with more than 80% accuracy. The thematic classification from ECHO showed the best agreement with ground reference samples. The residential area with relatively homogeneous composition was classified consistently with highest accuracy by all four of the classification methods used. The average accuracy amongst the classifiers was 93.60% for this area. When individually observed, the complex recreational area (Deming Park) was classified with the highest accuracy by ECHO, with an accuracy of 96.80% and 96.10% Kappa. The average accuracy amongst all the classifiers was 92.07%. The commercial area with relatively high complexity was classified with the least accuracy by all classifiers. The lowest accuracy was achieved by SAM at 63.90% with 59.20% Kappa. This was also the lowest accuracy in the entire analysis. This study demonstrates the potential for using the visible and near infrared (VNIR) bands from AISA+ hyperspectral data in urban LULC classification. Based on their performance, the need for further research using ECHO and SAM is underscored. The importance incorporating imaging spectrometer data in high resolution urban feature mapping is emphasized.

Pedestrian detection based on redundant wavelet transform

NASA Astrophysics Data System (ADS)

Huang, Lin; Ji, Liping; Hu, Ping; Yang, Tiejun

2016-10-01

Intelligent video surveillance is to analysis video or image sequences captured by a fixed or mobile surveillance camera, including moving object detection, segmentation and recognition. By using it, we can be notified immediately in an abnormal situation. Pedestrian detection plays an important role in an intelligent video surveillance system, and it is also a key technology in the field of intelligent vehicle. So pedestrian detection has very vital significance in traffic management optimization, security early warn and abnormal behavior detection. Generally, pedestrian detection can be summarized as: first to estimate moving areas; then to extract features of region of interest; finally to classify using a classifier. Redundant wavelet transform (RWT) overcomes the deficiency of shift variant of discrete wavelet transform, and it has better performance in motion estimation when compared to discrete wavelet transform. Addressing the problem of the detection of multi-pedestrian with different speed, we present an algorithm of pedestrian detection based on motion estimation using RWT, combining histogram of oriented gradients (HOG) and support vector machine (SVM). Firstly, three intensities of movement (IoM) are estimated using RWT and the corresponding areas are segmented. According to the different IoM, a region proposal (RP) is generated. Then, the features of a RP is extracted using HOG. Finally, the features are fed into a SVM trained by pedestrian databases and the final detection results are gained. Experiments show that the proposed algorithm can detect pedestrians accurately and efficiently.

Classification of large-scale fundus image data sets: a cloud-computing framework.

PubMed

Roychowdhury, Sohini

2016-08-01

Large medical image data sets with high dimensionality require substantial amount of computation time for data creation and data processing. This paper presents a novel generalized method that finds optimal image-based feature sets that reduce computational time complexity while maximizing overall classification accuracy for detection of diabetic retinopathy (DR). First, region-based and pixel-based features are extracted from fundus images for classification of DR lesions and vessel-like structures. Next, feature ranking strategies are used to distinguish the optimal classification feature sets. DR lesion and vessel classification accuracies are computed using the boosted decision tree and decision forest classifiers in the Microsoft Azure Machine Learning Studio platform, respectively. For images from the DIARETDB1 data set, 40 of its highest-ranked features are used to classify four DR lesion types with an average classification accuracy of 90.1% in 792 seconds. Also, for classification of red lesion regions and hemorrhages from microaneurysms, accuracies of 85% and 72% are observed, respectively. For images from STARE data set, 40 high-ranked features can classify minor blood vessels with an accuracy of 83.5% in 326 seconds. Such cloud-based fundus image analysis systems can significantly enhance the borderline classification performances in automated screening systems.

Heterogeneous Ensemble Combination Search Using Genetic Algorithm for Class Imbalanced Data Classification.

PubMed

Haque, Mohammad Nazmul; Noman, Nasimul; Berretta, Regina; Moscato, Pablo

2016-01-01

Classification of datasets with imbalanced sample distributions has always been a challenge. In general, a popular approach for enhancing classification performance is the construction of an ensemble of classifiers. However, the performance of an ensemble is dependent on the choice of constituent base classifiers. Therefore, we propose a genetic algorithm-based search method for finding the optimum combination from a pool of base classifiers to form a heterogeneous ensemble. The algorithm, called GA-EoC, utilises 10 fold-cross validation on training data for evaluating the quality of each candidate ensembles. In order to combine the base classifiers decision into ensemble's output, we used the simple and widely used majority voting approach. The proposed algorithm, along with the random sub-sampling approach to balance the class distribution, has been used for classifying class-imbalanced datasets. Additionally, if a feature set was not available, we used the (α, β) - k Feature Set method to select a better subset of features for classification. We have tested GA-EoC with three benchmarking datasets from the UCI-Machine Learning repository, one Alzheimer's disease dataset and a subset of the PubFig database of Columbia University. In general, the performance of the proposed method on the chosen datasets is robust and better than that of the constituent base classifiers and many other well-known ensembles. Based on our empirical study we claim that a genetic algorithm is a superior and reliable approach to heterogeneous ensemble construction and we expect that the proposed GA-EoC would perform consistently in other cases.

Heterogeneous Ensemble Combination Search Using Genetic Algorithm for Class Imbalanced Data Classification

PubMed Central

Haque, Mohammad Nazmul; Noman, Nasimul; Berretta, Regina; Moscato, Pablo

2016-01-01

Classification of datasets with imbalanced sample distributions has always been a challenge. In general, a popular approach for enhancing classification performance is the construction of an ensemble of classifiers. However, the performance of an ensemble is dependent on the choice of constituent base classifiers. Therefore, we propose a genetic algorithm-based search method for finding the optimum combination from a pool of base classifiers to form a heterogeneous ensemble. The algorithm, called GA-EoC, utilises 10 fold-cross validation on training data for evaluating the quality of each candidate ensembles. In order to combine the base classifiers decision into ensemble’s output, we used the simple and widely used majority voting approach. The proposed algorithm, along with the random sub-sampling approach to balance the class distribution, has been used for classifying class-imbalanced datasets. Additionally, if a feature set was not available, we used the (α, β) − k Feature Set method to select a better subset of features for classification. We have tested GA-EoC with three benchmarking datasets from the UCI-Machine Learning repository, one Alzheimer’s disease dataset and a subset of the PubFig database of Columbia University. In general, the performance of the proposed method on the chosen datasets is robust and better than that of the constituent base classifiers and many other well-known ensembles. Based on our empirical study we claim that a genetic algorithm is a superior and reliable approach to heterogeneous ensemble construction and we expect that the proposed GA-EoC would perform consistently in other cases. PMID:26764911

Comparison Between Supervised and Unsupervised Classifications of Neuronal Cell Types: A Case Study

PubMed Central

Guerra, Luis; McGarry, Laura M; Robles, Víctor; Bielza, Concha; Larrañaga, Pedro; Yuste, Rafael

2011-01-01

In the study of neural circuits, it becomes essential to discern the different neuronal cell types that build the circuit. Traditionally, neuronal cell types have been classified using qualitative descriptors. More recently, several attempts have been made to classify neurons quantitatively, using unsupervised clustering methods. While useful, these algorithms do not take advantage of previous information known to the investigator, which could improve the classification task. For neocortical GABAergic interneurons, the problem to discern among different cell types is particularly difficult and better methods are needed to perform objective classifications. Here we explore the use of supervised classification algorithms to classify neurons based on their morphological features, using a database of 128 pyramidal cells and 199 interneurons from mouse neocortex. To evaluate the performance of different algorithms we used, as a “benchmark,” the test to automatically distinguish between pyramidal cells and interneurons, defining “ground truth” by the presence or absence of an apical dendrite. We compared hierarchical clustering with a battery of different supervised classification algorithms, finding that supervised classifications outperformed hierarchical clustering. In addition, the selection of subsets of distinguishing features enhanced the classification accuracy for both sets of algorithms. The analysis of selected variables indicates that dendritic features were most useful to distinguish pyramidal cells from interneurons when compared with somatic and axonal morphological variables. We conclude that supervised classification algorithms are better matched to the general problem of distinguishing neuronal cell types when some information on these cell groups, in our case being pyramidal or interneuron, is known a priori. As a spin-off of this methodological study, we provide several methods to automatically distinguish neocortical pyramidal cells from interneurons, based on their morphologies. © 2010 Wiley Periodicals, Inc. Develop Neurobiol 71: 71–82, 2011 PMID:21154911

LDA boost classification: boosting by topics

NASA Astrophysics Data System (ADS)

Lei, La; Qiao, Guo; Qimin, Cao; Qitao, Li

2012-12-01

AdaBoost is an efficacious classification algorithm especially in text categorization (TC) tasks. The methodology of setting up a classifier committee and voting on the documents for classification can achieve high categorization precision. However, traditional Vector Space Model can easily lead to the curse of dimensionality and feature sparsity problems; so it affects classification performance seriously. This article proposed a novel classification algorithm called LDABoost based on boosting ideology which uses Latent Dirichlet Allocation (LDA) to modeling the feature space. Instead of using words or phrase, LDABoost use latent topics as the features. In this way, the feature dimension is significantly reduced. Improved Naïve Bayes (NB) is designed as the weaker classifier which keeps the efficiency advantage of classic NB algorithm and has higher precision. Moreover, a two-stage iterative weighted method called Cute Integration in this article is proposed for improving the accuracy by integrating weak classifiers into strong classifier in a more rational way. Mutual Information is used as metrics of weights allocation. The voting information and the categorization decision made by basis classifiers are fully utilized for generating the strong classifier. Experimental results reveals LDABoost making categorization in a low-dimensional space, it has higher accuracy than traditional AdaBoost algorithms and many other classic classification algorithms. Moreover, its runtime consumption is lower than different versions of AdaBoost, TC algorithms based on support vector machine and Neural Networks.

Detection of Delamination in Concrete Bridge Decks Using Mfcc of Acoustic Impact Signals

NASA Astrophysics Data System (ADS)

Zhang, G.; Harichandran, R. S.; Ramuhalli, P.

2010-02-01

Delamination of the concrete cover is a commonly observed damage in concrete bridge decks. The delamination is typically initiated by corrosion of the upper reinforcing bars and promoted by freeze-thaw cycling and traffic loading. The detection of delamination is important for bridge maintenance and acoustic non-destructive evaluation (NDE) is widely used due to its low cost, speed, and easy implementation. In traditional acoustic approaches, the inspector sounds the surface of the deck by impacting it with a hammer or bar, or by dragging a chain, and assesses delamination by the "hollowness" of the sound. The detection of the delamination is subjective and requires extensive training. To improve performance, this paper proposes an objective method for delamination detection. In this method, mel-frequency cepstral coefficients (MFCC) of the signal are extracted. Some MFCC are then selected as features for detection purposes using a mutual information criterion. Finally, the selected features are used to train a classifier which is subsequently used for detection. In this work, a simple quadratic Bayesian classifier is used. Different numbers of features are used to compare the performance of the detection method. The results show that the performance first increases with the number of features, but then decreases after an optimal value. The optimal number of features based on the recorded signals is four, and the mean error rate is only 3.3% when four features are used. Therefore, the proposed algorithm has sufficient accuracy to be used in field detection.

Cellular-automata-based learning network for pattern recognition

NASA Astrophysics Data System (ADS)

Tzionas, Panagiotis G.; Tsalides, Phillippos G.; Thanailakis, Adonios

1991-11-01

Most classification techniques either adopt an approach based directly on the statistical characteristics of the pattern classes involved, or they transform the patterns in a feature space and try to separate the point clusters in this space. An alternative approach based on memory networks has been presented, its novelty being that it can be implemented in parallel and it utilizes direct features of the patterns rather than statistical characteristics. This study presents a new approach for pattern classification using pseudo 2-D binary cellular automata (CA). This approach resembles the memory network classifier in the sense that it is based on an adaptive knowledge based formed during a training phase, and also in the fact that both methods utilize pattern features that are directly available. The main advantage of this approach is that the sensitivity of the pattern classifier can be controlled. The proposed pattern classifier has been designed using 1.5 micrometers design rules for an N-well CMOS process. Layout has been achieved using SOLO 1400. Binary pseudo 2-D hybrid additive CA (HACA) is described in the second section of this paper. The third section describes the operation of the pattern classifier and the fourth section presents some possible applications. The VLSI implementation of the pattern classifier is presented in the fifth section and, finally, the sixth section draws conclusions from the results obtained.

BCC skin cancer diagnosis based on texture analysis techniques

NASA Astrophysics Data System (ADS)

Chuang, Shao-Hui; Sun, Xiaoyan; Chang, Wen-Yu; Chen, Gwo-Shing; Huang, Adam; Li, Jiang; McKenzie, Frederic D.

2011-03-01

In this paper, we present a texture analysis based method for diagnosing the Basal Cell Carcinoma (BCC) skin cancer using optical images taken from the suspicious skin regions. We first extracted the Run Length Matrix and Haralick texture features from the images and used a feature selection algorithm to identify the most effective feature set for the diagnosis. We then utilized a Multi-Layer Perceptron (MLP) classifier to classify the images to BCC or normal cases. Experiments showed that detecting BCC cancer based on optical images is feasible. The best sensitivity and specificity we achieved on our data set were 94% and 95%, respectively.

Thin Cloud Detection Method by Linear Combination Model of Cloud Image

NASA Astrophysics Data System (ADS)

Liu, L.; Li, J.; Wang, Y.; Xiao, Y.; Zhang, W.; Zhang, S.

2018-04-01

The existing cloud detection methods in photogrammetry often extract the image features from remote sensing images directly, and then use them to classify images into cloud or other things. But when the cloud is thin and small, these methods will be inaccurate. In this paper, a linear combination model of cloud images is proposed, by using this model, the underlying surface information of remote sensing images can be removed. So the cloud detection result can become more accurate. Firstly, the automatic cloud detection program in this paper uses the linear combination model to split the cloud information and surface information in the transparent cloud images, then uses different image features to recognize the cloud parts. In consideration of the computational efficiency, AdaBoost Classifier was introduced to combine the different features to establish a cloud classifier. AdaBoost Classifier can select the most effective features from many normal features, so the calculation time is largely reduced. Finally, we selected a cloud detection method based on tree structure and a multiple feature detection method using SVM classifier to compare with the proposed method, the experimental data shows that the proposed cloud detection program in this paper has high accuracy and fast calculation speed.

A novel approach for fire recognition using hybrid features and manifold learning-based classifier

NASA Astrophysics Data System (ADS)

Zhu, Rong; Hu, Xueying; Tang, Jiajun; Hu, Sheng

2018-03-01

Although image/video based fire recognition has received growing attention, an efficient and robust fire detection strategy is rarely explored. In this paper, we propose a novel approach to automatically identify the flame or smoke regions in an image. It is composed to three stages: (1) a block processing is applied to divide an image into several nonoverlapping image blocks, and these image blocks are identified as suspicious fire regions or not by using two color models and a color histogram-based similarity matching method in the HSV color space, (2) considering that compared to other information, the flame and smoke regions have significant visual characteristics, so that two kinds of image features are extracted for fire recognition, where local features are obtained based on the Scale Invariant Feature Transform (SIFT) descriptor and the Bags of Keypoints (BOK) technique, and texture features are extracted based on the Gray Level Co-occurrence Matrices (GLCM) and the Wavelet-based Analysis (WA) methods, and (3) a manifold learning-based classifier is constructed based on two image manifolds, which is designed via an improve Globular Neighborhood Locally Linear Embedding (GNLLE) algorithm, and the extracted hybrid features are used as input feature vectors to train the classifier, which is used to make decision for fire images or non fire images. Experiments and comparative analyses with four approaches are conducted on the collected image sets. The results show that the proposed approach is superior to the other ones in detecting fire and achieving a high recognition accuracy and a low error rate.

A review of supervised object-based land-cover image classification

NASA Astrophysics Data System (ADS)

Ma, Lei; Li, Manchun; Ma, Xiaoxue; Cheng, Liang; Du, Peijun; Liu, Yongxue

2017-08-01

Object-based image classification for land-cover mapping purposes using remote-sensing imagery has attracted significant attention in recent years. Numerous studies conducted over the past decade have investigated a broad array of sensors, feature selection, classifiers, and other factors of interest. However, these research results have not yet been synthesized to provide coherent guidance on the effect of different supervised object-based land-cover classification processes. In this study, we first construct a database with 28 fields using qualitative and quantitative information extracted from 254 experimental cases described in 173 scientific papers. Second, the results of the meta-analysis are reported, including general characteristics of the studies (e.g., the geographic range of relevant institutes, preferred journals) and the relationships between factors of interest (e.g., spatial resolution and study area or optimal segmentation scale, accuracy and number of targeted classes), especially with respect to the classification accuracy of different sensors, segmentation scale, training set size, supervised classifiers, and land-cover types. Third, useful data on supervised object-based image classification are determined from the meta-analysis. For example, we find that supervised object-based classification is currently experiencing rapid advances, while development of the fuzzy technique is limited in the object-based framework. Furthermore, spatial resolution correlates with the optimal segmentation scale and study area, and Random Forest (RF) shows the best performance in object-based classification. The area-based accuracy assessment method can obtain stable classification performance, and indicates a strong correlation between accuracy and training set size, while the accuracy of the point-based method is likely to be unstable due to mixed objects. In addition, the overall accuracy benefits from higher spatial resolution images (e.g., unmanned aerial vehicle) or agricultural sites where it also correlates with the number of targeted classes. More than 95.6% of studies involve an area less than 300 ha, and the spatial resolution of images is predominantly between 0 and 2 m. Furthermore, we identify some methods that may advance supervised object-based image classification. For example, deep learning and type-2 fuzzy techniques may further improve classification accuracy. Lastly, scientists are strongly encouraged to report results of uncertainty studies to further explore the effects of varied factors on supervised object-based image classification.

Application of the Teager-Kaiser energy operator in bearing fault diagnosis.

PubMed

Henríquez Rodríguez, Patricia; Alonso, Jesús B; Ferrer, Miguel A; Travieso, Carlos M

2013-03-01

Condition monitoring of rotating machines is important in the prevention of failures. As most machine malfunctions are related to bearing failures, several bearing diagnosis techniques have been developed. Some of them feature the bearing vibration signal with statistical measures and others extract the bearing fault characteristic frequency from the AM component of the vibration signal. In this paper, we propose to transform the vibration signal to the Teager-Kaiser domain and feature it with statistical and energy-based measures. A bearing database with normal and faulty bearings is used. The diagnosis is performed with two classifiers: a neural network classifier and a LS-SVM classifier. Experiments show that the Teager domain features outperform those based on the temporal or AM signal. Copyright © 2012 ISA. Published by Elsevier Ltd. All rights reserved.

Comparative analysis of classification based algorithms for diabetes diagnosis using iris images.

PubMed

Samant, Piyush; Agarwal, Ravinder

2018-01-01

Photo-diagnosis is always an intriguing area for the researchers, with the advancement of image processing and computer machine vision techniques it have become more reliable and popular in recent years. The objective of this paper is to study the change in the features of iris, particularly irregularities in the pigmentation of certain areas of the iris with respect to diabetic health of an individual. Apart from the point that iris recognition concentrates on the overall structure of the iris, diagnostic techniques emphasises the local variations in the particular area of iris. Pre-image processing techniques have been applied to extract iris and thereafter, region of interest from the extracted iris have been cropped out. In order to observe the changes in the tissue pigmentation of region of interest, statistical, texture textural and wavelet features have been extracted. At the end, a comparison of accuracies of five different classifiers has been presented to classify two subject groups of diabetic and non-diabetic. Best classification accuracy has been calculated as 89.66% by the random forest classifier. Results have been shown the effectiveness and diagnostic significance of the proposed methodology. Presented piece of work offers a novel systemic perspective of non-invasive and automatic diabetic diagnosis.

Pharmacokinetic Tumor Heterogeneity as a Prognostic Biomarker for Classifying Breast Cancer Recurrence Risk.

PubMed

Mahrooghy, Majid; Ashraf, Ahmed B; Daye, Dania; McDonald, Elizabeth S; Rosen, Mark; Mies, Carolyn; Feldman, Michael; Kontos, Despina

2015-06-01

Heterogeneity in cancer can affect response to therapy and patient prognosis. Histologic measures have classically been used to measure heterogeneity, although a reliable noninvasive measurement is needed both to establish baseline risk of recurrence and monitor response to treatment. Here, we propose using spatiotemporal wavelet kinetic features from dynamic contrast-enhanced magnetic resonance imaging to quantify intratumor heterogeneity in breast cancer. Tumor pixels are first partitioned into homogeneous subregions using pharmacokinetic measures. Heterogeneity wavelet kinetic (HetWave) features are then extracted from these partitions to obtain spatiotemporal patterns of the wavelet coefficients and the contrast agent uptake. The HetWave features are evaluated in terms of their prognostic value using a logistic regression classifier with genetic algorithm wrapper-based feature selection to classify breast cancer recurrence risk as determined by a validated gene expression assay. Receiver operating characteristic analysis and area under the curve (AUC) are computed to assess classifier performance using leave-one-out cross validation. The HetWave features outperform other commonly used features (AUC = 0.88 HetWave versus 0.70 standard features). The combination of HetWave and standard features further increases classifier performance (AUCs 0.94). The rate of the spatial frequency pattern over the pharmacokinetic partitions can provide valuable prognostic information. HetWave could be a powerful feature extraction approach for characterizing tumor heterogeneity, providing valuable prognostic information.

ECG Based Heart Arrhythmia Detection Using Wavelet Coherence and Bat Algorithm

NASA Astrophysics Data System (ADS)

Kora, Padmavathi; Sri Rama Krishna, K.

2016-12-01

Atrial fibrillation (AF) is a type of heart abnormality, during the AF electrical discharges in the atrium are rapid, results in abnormal heart beat. The morphology of ECG changes due to the abnormalities in the heart. This paper consists of three major steps for the detection of heart diseases: signal pre-processing, feature extraction and classification. Feature extraction is the key process in detecting the heart abnormality. Most of the ECG detection systems depend on the time domain features for cardiac signal classification. In this paper we proposed a wavelet coherence (WTC) technique for ECG signal analysis. The WTC calculates the similarity between two waveforms in frequency domain. Parameters extracted from WTC function is used as the features of the ECG signal. These features are optimized using Bat algorithm. The Levenberg Marquardt neural network classifier is used to classify the optimized features. The performance of the classifier can be improved with the optimized features.

GIS coupled Multiple Criteria based Decision Support for Classification of Urban Coastal Areas in India

NASA Astrophysics Data System (ADS)

Dhiman, R.; Kalbar, P.; Inamdar, A. B.

2017-12-01

Coastal area classification in India is a challenge for federal and state government agencies due to fragile institutional framework, unclear directions in implementation of costal regulations and violations happening at private and government level. This work is an attempt to improvise the objectivity of existing classification methods to synergies the ecological systems and socioeconomic development in coastal cities. We developed a Geographic information system coupled Multi-criteria Decision Making (GIS-MCDM) approach to classify urban coastal areas where utility functions are used to transform the costal features into quantitative membership values after assessing the sensitivity of urban coastal ecosystem. Furthermore, these membership values for costal features are applied in different weighting schemes to derive Coastal Area Index (CAI) which classifies the coastal areas in four distinct categories viz. 1) No Development Zone, 2) Highly Sensitive Zone, 3) Moderately Sensitive Zone and 4) Low Sensitive Zone based on the sensitivity of urban coastal ecosystem. Mumbai, a coastal megacity in India is used as case study for demonstration of proposed method. Finally, uncertainty analysis using Monte Carlo approach to validate the sensitivity of CAI under specific multiple scenarios is carried out. Results of CAI method shows the clear demarcation of coastal areas in GIS environment based on the ecological sensitivity. CAI provides better decision support for federal and state level agencies to classify urban coastal areas according to the regional requirement of coastal resources considering resilience and sustainable development. CAI method will strengthen the existing institutional framework for decision making in classification of urban coastal areas where most effective coastal management options can be proposed.

Automated in vivo identification of fungal infection on human scalp using optical coherence tomography and machine learning

NASA Astrophysics Data System (ADS)

Dubey, Kavita; Srivastava, Vishal; Singh Mehta, Dalip

2018-04-01

Early identification of fungal infection on the human scalp is crucial for avoiding hair loss. The diagnosis of fungal infection on the human scalp is based on a visual assessment by trained experts or doctors. Optical coherence tomography (OCT) has the ability to capture fungal infection information from the human scalp with a high resolution. In this study, we present a fully automated, non-contact, non-invasive optical method for rapid detection of fungal infections based on the extracted features from A-line and B-scan images of OCT. A multilevel ensemble machine model is designed to perform automated classification, which shows the superiority of our classifier to the best classifier based on the features extracted from OCT images. In this study, 60 samples (30 fungal, 30 normal) were imaged by OCT and eight features were extracted. The classification algorithm had an average sensitivity, specificity and accuracy of 92.30, 90.90 and 91.66%, respectively, for identifying fungal and normal human scalps. This remarkable classifying ability makes the proposed model readily applicable to classifying the human scalp.

Classification of CT examinations for COPD visual severity analysis

NASA Astrophysics Data System (ADS)

Tan, Jun; Zheng, Bin; Wang, Xingwei; Pu, Jiantao; Gur, David; Sciurba, Frank C.; Leader, J. Ken

2012-03-01

In this study we present a computational method of CT examination classification into visual assessed emphysema severity. The visual severity categories ranged from 0 to 5 and were rated by an experienced radiologist. The six categories were none, trace, mild, moderate, severe and very severe. Lung segmentation was performed for every input image and all image features are extracted from the segmented lung only. We adopted a two-level feature representation method for the classification. Five gray level distribution statistics, six gray level co-occurrence matrix (GLCM), and eleven gray level run-length (GLRL) features were computed for each CT image depicted segment lung. Then we used wavelets decomposition to obtain the low- and high-frequency components of the input image, and again extract from the lung region six GLCM features and eleven GLRL features. Therefore our feature vector length is 56. The CT examinations were classified using the support vector machine (SVM) and k-nearest neighbors (KNN) and the traditional threshold (density mask) approach. The SVM classifier had the highest classification performance of all the methods with an overall sensitivity of 54.4% and a 69.6% sensitivity to discriminate "no" and "trace visually assessed emphysema. We believe this work may lead to an automated, objective method to categorically classify emphysema severity on CT exam.

Introduction to the GEOBIA 2010 special issue: From pixels to geographic objects in remote sensing image analysis

NASA Astrophysics Data System (ADS)

Addink, Elisabeth A.; Van Coillie, Frieke M. B.; De Jong, Steven M.

2012-04-01

Traditional image analysis methods are mostly pixel-based and use the spectral differences of landscape elements at the Earth surface to classify these elements or to extract element properties from the Earth Observation image. Geographic object-based image analysis (GEOBIA) has received considerable attention over the past 15 years for analyzing and interpreting remote sensing imagery. In contrast to traditional image analysis, GEOBIA works more like the human eye-brain combination does. The latter uses the object's color (spectral information), size, texture, shape and occurrence to other image objects to interpret and analyze what we see. GEOBIA starts by segmenting the image grouping together pixels into objects and next uses a wide range of object properties to classify the objects or to extract object's properties from the image. Significant advances and improvements in image analysis and interpretation are made thanks to GEOBIA. In June 2010 the third conference on GEOBIA took place at the Ghent University after successful previous meetings in Calgary (2008) and Salzburg (2006). This special issue presents a selection of the 2010 conference papers that are worked out as full research papers for JAG. The papers cover GEOBIA applications as well as innovative methods and techniques. The topics range from vegetation mapping, forest parameter estimation, tree crown identification, urban mapping, land cover change, feature selection methods and the effects of image compression on segmentation. From the original 94 conference papers, 26 full research manuscripts were submitted; nine papers were selected and are presented in this special issue. Selection was done on the basis of quality and topic of the studies. The next GEOBIA conference will take place in Rio de Janeiro from 7 to 9 May 2012 where we hope to welcome even more scientists working in the field of GEOBIA.

Classification of biosensor time series using dynamic time warping: applications in screening cancer cells with characteristic biomarkers.

PubMed

Rai, Shesh N; Trainor, Patrick J; Khosravi, Farhad; Kloecker, Goetz; Panchapakesan, Balaji

2016-01-01

The development of biosensors that produce time series data will facilitate improvements in biomedical diagnostics and in personalized medicine. The time series produced by these devices often contains characteristic features arising from biochemical interactions between the sample and the sensor. To use such characteristic features for determining sample class, similarity-based classifiers can be utilized. However, the construction of such classifiers is complicated by the variability in the time domains of such series that renders the traditional distance metrics such as Euclidean distance ineffective in distinguishing between biological variance and time domain variance. The dynamic time warping (DTW) algorithm is a sequence alignment algorithm that can be used to align two or more series to facilitate quantifying similarity. In this article, we evaluated the performance of DTW distance-based similarity classifiers for classifying time series that mimics electrical signals produced by nanotube biosensors. Simulation studies demonstrated the positive performance of such classifiers in discriminating between time series containing characteristic features that are obscured by noise in the intensity and time domains. We then applied a DTW distance-based k -nearest neighbors classifier to distinguish the presence/absence of mesenchymal biomarker in cancer cells in buffy coats in a blinded test. Using a train-test approach, we find that the classifier had high sensitivity (90.9%) and specificity (81.8%) in differentiating between EpCAM-positive MCF7 cells spiked in buffy coats and those in plain buffy coats.

Evaluation of different classification methods for the diagnosis of schizophrenia based on functional near-infrared spectroscopy.

PubMed

Li, Zhaohua; Wang, Yuduo; Quan, Wenxiang; Wu, Tongning; Lv, Bin

2015-02-15

Based on near-infrared spectroscopy (NIRS), recent converging evidence has been observed that patients with schizophrenia exhibit abnormal functional activities in the prefrontal cortex during a verbal fluency task (VFT). Therefore, some studies have attempted to employ NIRS measurements to differentiate schizophrenia patients from healthy controls with different classification methods. However, no systematic evaluation was conducted to compare their respective classification performances on the same study population. In this study, we evaluated the classification performance of four classification methods (including linear discriminant analysis, k-nearest neighbors, Gaussian process classifier, and support vector machines) on an NIRS-aided schizophrenia diagnosis. We recruited a large sample of 120 schizophrenia patients and 120 healthy controls and measured the hemoglobin response in the prefrontal cortex during the VFT using a multichannel NIRS system. Features for classification were extracted from three types of NIRS data in each channel. We subsequently performed a principal component analysis (PCA) for feature selection prior to comparison of the different classification methods. We achieved a maximum accuracy of 85.83% and an overall mean accuracy of 83.37% using a PCA-based feature selection on oxygenated hemoglobin signals and support vector machine classifier. This is the first comprehensive evaluation of different classification methods for the diagnosis of schizophrenia based on different types of NIRS signals. Our results suggested that, using the appropriate classification method, NIRS has the potential capacity to be an effective objective biomarker for the diagnosis of schizophrenia. Copyright © 2014 Elsevier B.V. All rights reserved.

A novel fuzzy approach for automatic Brunnstrom stage classification using surface electromyography.

PubMed

Liparulo, Luca; Zhang, Zhe; Panella, Massimo; Gu, Xudong; Fang, Qiang

2017-08-01

Clinical assessment plays a major role in post-stroke rehabilitation programs for evaluating impairment level and tracking recovery progress. Conventionally, this process is manually performed by clinicians using chart-based ordinal scales which can be both subjective and inefficient. In this paper, a novel approach based on fuzzy logic is proposed which automatically evaluates stroke patients' impairment level using single-channel surface electromyography (sEMG) signals and generates objective classification results based on the widely used Brunnstrom stages of recovery. The correlation between stroke-induced motor impairment and sEMG features on both time and frequency domain is investigated, and a specifically designed fuzzy kernel classifier based on geometrically unconstrained membership function is introduced in the study to tackle the challenges in discriminating data classes with complex separating surfaces. Experiments using sEMG data collected from stroke patients have been carried out to examine the validity and feasibility of the proposed method. In order to ensure the generalization capability of the classifier, a cross-validation test has been performed. The results, verified using the evaluation decisions provided by an expert panel, have reached a rate of success of the 92.47%. The proposed fuzzy classifier is also compared with other pattern recognition techniques to demonstrate its superior performance in this application.

Classifying Facial Actions

PubMed Central

Donato, Gianluca; Bartlett, Marian Stewart; Hager, Joseph C.; Ekman, Paul; Sejnowski, Terrence J.

2010-01-01

The Facial Action Coding System (FACS) [23] is an objective method for quantifying facial movement in terms of component actions. This system is widely used in behavioral investigations of emotion, cognitive processes, and social interaction. The coding is presently performed by highly trained human experts. This paper explores and compares techniques for automatically recognizing facial actions in sequences of images. These techniques include analysis of facial motion through estimation of optical flow; holistic spatial analysis, such as principal component analysis, independent component analysis, local feature analysis, and linear discriminant analysis; and methods based on the outputs of local filters, such as Gabor wavelet representations and local principal components. Performance of these systems is compared to naive and expert human subjects. Best performances were obtained using the Gabor wavelet representation and the independent component representation, both of which achieved 96 percent accuracy for classifying 12 facial actions of the upper and lower face. The results provide converging evidence for the importance of using local filters, high spatial frequencies, and statistical independence for classifying facial actions. PMID:21188284

Approach to explosive hazard detection using sensor fusion and multiple kernel learning with downward-looking GPR and EMI sensor data

NASA Astrophysics Data System (ADS)

Pinar, Anthony; Masarik, Matthew; Havens, Timothy C.; Burns, Joseph; Thelen, Brian; Becker, John

2015-05-01

This paper explores the effectiveness of an anomaly detection algorithm for downward-looking ground penetrating radar (GPR) and electromagnetic inductance (EMI) data. Threat detection with GPR is challenged by high responses to non-target/clutter objects, leading to a large number of false alarms (FAs), and since the responses of target and clutter signatures are so similar, classifier design is not trivial. We suggest a method based on a Run Packing (RP) algorithm to fuse GPR and EMI data into a composite confidence map to improve detection as measured by the area-under-ROC (NAUC) metric. We examine the value of a multiple kernel learning (MKL) support vector machine (SVM) classifier using image features such as histogram of oriented gradients (HOG), local binary patterns (LBP), and local statistics. Experimental results on government furnished data show that use of our proposed fusion and classification methods improves the NAUC when compared with the results from individual sensors and a single kernel SVM classifier.

A Filter Feature Selection Method Based on MFA Score and Redundancy Excluding and It's Application to Tumor Gene Expression Data Analysis.

PubMed

Li, Jiangeng; Su, Lei; Pang, Zenan

2015-12-01

Feature selection techniques have been widely applied to tumor gene expression data analysis in recent years. A filter feature selection method named marginal Fisher analysis score (MFA score) which is based on graph embedding has been proposed, and it has been widely used mainly because it is superior to Fisher score. Considering the heavy redundancy in gene expression data, we proposed a new filter feature selection technique in this paper. It is named MFA score+ and is based on MFA score and redundancy excluding. We applied it to an artificial dataset and eight tumor gene expression datasets to select important features and then used support vector machine as the classifier to classify the samples. Compared with MFA score, t test and Fisher score, it achieved higher classification accuracy.

Brain metabolic pattern analysis using a magnetic resonance spectra classification software in experimental stroke.

PubMed

Jiménez-Xarrié, Elena; Davila, Myriam; Candiota, Ana Paula; Delgado-Mederos, Raquel; Ortega-Martorell, Sandra; Julià-Sapé, Margarida; Arús, Carles; Martí-Fàbregas, Joan

2017-01-13

Magnetic resonance spectroscopy (MRS) provides non-invasive information about the metabolic pattern of the brain parenchyma in vivo. The SpectraClassifier software performs MRS pattern-recognition by determining the spectral features (metabolites) which can be used objectively to classify spectra. Our aim was to develop an Infarct Evolution Classifier and a Brain Regions Classifier in a rat model of focal ischemic stroke using SpectraClassifier. A total of 164 single-voxel proton spectra obtained with a 7 Tesla magnet at an echo time of 12 ms from non-infarcted parenchyma, subventricular zones and infarcted parenchyma were analyzed with SpectraClassifier ( http://gabrmn.uab.es/?q=sc ). The spectra corresponded to Sprague-Dawley rats (healthy rats, n = 7) and stroke rats at day 1 post-stroke (acute phase, n = 6 rats) and at days 7 ± 1 post-stroke (subacute phase, n = 14). In the Infarct Evolution Classifier, spectral features contributed by lactate + mobile lipids (1.33 ppm), total creatine (3.05 ppm) and mobile lipids (0.85 ppm) distinguished among non-infarcted parenchyma (100% sensitivity and 100% specificity), acute phase of infarct (100% sensitivity and 95% specificity) and subacute phase of infarct (78% sensitivity and 100% specificity). In the Brain Regions Classifier, spectral features contributed by myoinositol (3.62 ppm) and total creatine (3.04/3.05 ppm) distinguished among infarcted parenchyma (100% sensitivity and 98% specificity), non-infarcted parenchyma (84% sensitivity and 84% specificity) and subventricular zones (76% sensitivity and 93% specificity). SpectraClassifier identified candidate biomarkers for infarct evolution (mobile lipids accumulation) and different brain regions (myoinositol content).

A method of evolving novel feature extraction algorithms for detecting buried objects in FLIR imagery using genetic programming

NASA Astrophysics Data System (ADS)

Paino, A.; Keller, J.; Popescu, M.; Stone, K.

2014-06-01

In this paper we present an approach that uses Genetic Programming (GP) to evolve novel feature extraction algorithms for greyscale images. Our motivation is to create an automated method of building new feature extraction algorithms for images that are competitive with commonly used human-engineered features, such as Local Binary Pattern (LBP) and Histogram of Oriented Gradients (HOG). The evolved feature extraction algorithms are functions defined over the image space, and each produces a real-valued feature vector of variable length. Each evolved feature extractor breaks up the given image into a set of cells centered on every pixel, performs evolved operations on each cell, and then combines the results of those operations for every cell using an evolved operator. Using this method, the algorithm is flexible enough to reproduce both LBP and HOG features. The dataset we use to train and test our approach consists of a large number of pre-segmented image "chips" taken from a Forward Looking Infrared Imagery (FLIR) camera mounted on the hood of a moving vehicle. The goal is to classify each image chip as either containing or not containing a buried object. To this end, we define the fitness of a candidate solution as the cross-fold validation accuracy of the features generated by said candidate solution when used in conjunction with a Support Vector Machine (SVM) classifier. In order to validate our approach, we compare the classification accuracy of an SVM trained using our evolved features with the accuracy of an SVM trained using mainstream feature extraction algorithms, including LBP and HOG.

LCC: Light Curves Classifier

NASA Astrophysics Data System (ADS)

Vo, Martin

2017-08-01

Light Curves Classifier uses data mining and machine learning to obtain and classify desired objects. This task can be accomplished by attributes of light curves or any time series, including shapes, histograms, or variograms, or by other available information about the inspected objects, such as color indices, temperatures, and abundances. After specifying features which describe the objects to be searched, the software trains on a given training sample, and can then be used for unsupervised clustering for visualizing the natural separation of the sample. The package can be also used for automatic tuning parameters of used methods (for example, number of hidden neurons or binning ratio). Trained classifiers can be used for filtering outputs from astronomical databases or data stored locally. The Light Curve Classifier can also be used for simple downloading of light curves and all available information of queried stars. It natively can connect to OgleII, OgleIII, ASAS, CoRoT, Kepler, Catalina and MACHO, and new connectors or descriptors can be implemented. In addition to direct usage of the package and command line UI, the program can be used through a web interface. Users can create jobs for ”training” methods on given objects, querying databases and filtering outputs by trained filters. Preimplemented descriptors, classifier and connectors can be picked by simple clicks and their parameters can be tuned by giving ranges of these values. All combinations are then calculated and the best one is used for creating the filter. Natural separation of the data can be visualized by unsupervised clustering.

Invariant-feature-based adaptive automatic target recognition in obscured 3D point clouds

NASA Astrophysics Data System (ADS)

Khuon, Timothy; Kershner, Charles; Mattei, Enrico; Alverio, Arnel; Rand, Robert

2014-06-01

Target recognition and classification in a 3D point cloud is a non-trivial process due to the nature of the data collected from a sensor system. The signal can be corrupted by noise from the environment, electronic system, A/D converter, etc. Therefore, an adaptive system with a desired tolerance is required to perform classification and recognition optimally. The feature-based pattern recognition algorithm architecture as described below is particularly devised for solving a single-sensor classification non-parametrically. Feature set is extracted from an input point cloud, normalized, and classifier a neural network classifier. For instance, automatic target recognition in an urban area would require different feature sets from one in a dense foliage area. The figure above (see manuscript) illustrates the architecture of the feature based adaptive signature extraction of 3D point cloud including LIDAR, RADAR, and electro-optical data. This network takes a 3D cluster and classifies it into a specific class. The algorithm is a supervised and adaptive classifier with two modes: the training mode and the performing mode. For the training mode, a number of novel patterns are selected from actual or artificial data. A particular 3D cluster is input to the network as shown above for the decision class output. The network consists of three sequential functional modules. The first module is for feature extraction that extracts the input cluster into a set of singular value features or feature vector. Then the feature vector is input into the feature normalization module to normalize and balance it before being fed to the neural net classifier for the classification. The neural net can be trained by actual or artificial novel data until each trained output reaches the declared output within the defined tolerance. In case new novel data is added after the neural net has been learned, the training is then resumed until the neural net has incrementally learned with the new novel data. The associative memory capability of the neural net enables the incremental learning. The back propagation algorithm or support vector machine can be utilized for the classification and recognition.

The Emotion Recognition System Based on Autoregressive Model and Sequential Forward Feature Selection of Electroencephalogram Signals

PubMed Central

Hatamikia, Sepideh; Maghooli, Keivan; Nasrabadi, Ali Motie

2014-01-01

Electroencephalogram (EEG) is one of the useful biological signals to distinguish different brain diseases and mental states. In recent years, detecting different emotional states from biological signals has been merged more attention by researchers and several feature extraction methods and classifiers are suggested to recognize emotions from EEG signals. In this research, we introduce an emotion recognition system using autoregressive (AR) model, sequential forward feature selection (SFS) and K-nearest neighbor (KNN) classifier using EEG signals during emotional audio-visual inductions. The main purpose of this paper is to investigate the performance of AR features in the classification of emotional states. To achieve this goal, a distinguished AR method (Burg's method) based on Levinson-Durbin's recursive algorithm is used and AR coefficients are extracted as feature vectors. In the next step, two different feature selection methods based on SFS algorithm and Davies–Bouldin index are used in order to decrease the complexity of computing and redundancy of features; then, three different classifiers include KNN, quadratic discriminant analysis and linear discriminant analysis are used to discriminate two and three different classes of valence and arousal levels. The proposed method is evaluated with EEG signals of available database for emotion analysis using physiological signals, which are recorded from 32 participants during 40 1 min audio visual inductions. According to the results, AR features are efficient to recognize emotional states from EEG signals, and KNN performs better than two other classifiers in discriminating of both two and three valence/arousal classes. The results also show that SFS method improves accuracies by almost 10-15% as compared to Davies–Bouldin based feature selection. The best accuracies are %72.33 and %74.20 for two classes of valence and arousal and %61.10 and %65.16 for three classes, respectively. PMID:25298928

A time-frequency classifier for human gait recognition

NASA Astrophysics Data System (ADS)

Mobasseri, Bijan G.; Amin, Moeness G.

2009-05-01

Radar has established itself as an effective all-weather, day or night sensor. Radar signals can penetrate walls and provide information on moving targets. Recently, radar has been used as an effective biometric sensor for classification of gait. The return from a coherent radar system contains a frequency offset in the carrier frequency, known as the Doppler Effect. The movements of arms and legs give rise to micro Doppler which can be clearly detailed in the time-frequency domain using traditional or modern time-frequency signal representation. In this paper we propose a gait classifier based on subspace learning using principal components analysis(PCA). The training set consists of feature vectors defined as either time or frequency snapshots taken from the spectrogram of radar backscatter. We show that gait signature is captured effectively in feature vectors. Feature vectors are then used in training a minimum distance classifier based on Mahalanobis distance metric. Results show that gait classification with high accuracy and short observation window is achievable using the proposed classifier.

Automated solar collector installation design

DOEpatents

Wayne, Gary; Frumkin, Alexander; Zaydman, Michael; Lehman, Scott; Brenner, Jules

2014-08-26

Embodiments may include systems and methods to create and edit a representation of a worksite, to create various data objects, to classify such objects as various types of pre-defined "features" with attendant properties and layout constraints. As part of or in addition to classification, an embodiment may include systems and methods to create, associate, and edit intrinsic and extrinsic properties to these objects. A design engine may apply of design rules to the features described above to generate one or more solar collectors installation design alternatives, including generation of on-screen and/or paper representations of the physical layout or arrangement of the one or more design alternatives.

Earthquake damage mapping by using remotely sensed data: the Haiti case study

NASA Astrophysics Data System (ADS)

Romaniello, Vito; Piscini, Alessandro; Bignami, Christian; Anniballe, Roberta; Stramondo, Salvatore

2017-01-01

This work proposes methodologies aimed at evaluating the sensitivity of optical and synthetic aperture radar (SAR) change features obtained from satellite images with respect to the damage grade due to an earthquake. The test case is the Mw 7.0 earthquake that hit Haiti on January 12, 2010, located 25 km west-south-west of the city of Port-au-Prince. The disastrous shock caused the collapse of a huge number of buildings and widespread damage. The objective is to investigate possible parameters that can affect the robustness and sensitivity of the proposed methods derived from the literature. It is worth noting how the proposed analysis concerns the estimation of derived features at object scale. For this purpose, a segmentation of the study area into several regions has been done by considering a set of polygons, over the city of Port-au-Prince, extracted from the open source open street map geo-database. The analysis of change detection indicators is based on ground truth information collected during a postearthquake survey and is available from a Joint Research Centre database. The resulting damage map is expressed in terms of collapse ratio, thus indicating the areas with a greater number of collapsed buildings. The available satellite dataset is composed of optical and SAR images, collected before and after the seismic event. In particular, we used two GeoEye-1 optical images (one preseismic and one postseismic) and three TerraSAR-X SAR images (two preseismic and one postseismic). Previous studies allowed us to identify some features having a good sensitivity with damage at the object scale. Regarding the optical data, we selected the normalized difference index and two quantities coming from the information theory, namely the Kullback-Libler divergence (KLD) and the mutual information (MI). In addition, for the SAR data, we picked out the intensity correlation difference and the KLD parameter. In order to analyze the capability of these parameters to correctly detect damaged areas, two different classifiers were used: the Naive Bayes and the support vector machine classifiers. The classification results demonstrate that the simultaneous use of several change features from Earth observations can improve the damage estimation at object scale.

Machine learning-based quantitative texture analysis of CT images of small renal masses: Differentiation of angiomyolipoma without visible fat from renal cell carcinoma.

PubMed

Feng, Zhichao; Rong, Pengfei; Cao, Peng; Zhou, Qingyu; Zhu, Wenwei; Yan, Zhimin; Liu, Qianyun; Wang, Wei

2018-04-01

To evaluate the diagnostic performance of machine-learning based quantitative texture analysis of CT images to differentiate small (≤ 4 cm) angiomyolipoma without visible fat (AMLwvf) from renal cell carcinoma (RCC). This single-institutional retrospective study included 58 patients with pathologically proven small renal mass (17 in AMLwvf and 41 in RCC groups). Texture features were extracted from the largest possible tumorous regions of interest (ROIs) by manual segmentation in preoperative three-phase CT images. Interobserver reliability and the Mann-Whitney U test were applied to select features preliminarily. Then support vector machine with recursive feature elimination (SVM-RFE) and synthetic minority oversampling technique (SMOTE) were adopted to establish discriminative classifiers, and the performance of classifiers was assessed. Of the 42 extracted features, 16 candidate features showed significant intergroup differences (P < 0.05) and had good interobserver agreement. An optimal feature subset including 11 features was further selected by the SVM-RFE method. The SVM-RFE+SMOTE classifier achieved the best performance in discriminating between small AMLwvf and RCC, with the highest accuracy, sensitivity, specificity and AUC of 93.9 %, 87.8 %, 100 % and 0.955, respectively. Machine learning analysis of CT texture features can facilitate the accurate differentiation of small AMLwvf from RCC. • Although conventional CT is useful for diagnosis of SRMs, it has limitations. • Machine-learning based CT texture analysis facilitate differentiation of small AMLwvf from RCC. • The highest accuracy of SVM-RFE+SMOTE classifier reached 93.9 %. • Texture analysis combined with machine-learning methods might spare unnecessary surgery for AMLwvf.

Automated tissue classification of intracardiac optical coherence tomography images (Conference Presentation)

NASA Astrophysics Data System (ADS)

Gan, Yu; Tsay, David; Amir, Syed B.; Marboe, Charles C.; Hendon, Christine P.

2016-03-01

Remodeling of the myocardium is associated with increased risk of arrhythmia and heart failure. Our objective is to automatically identify regions of fibrotic myocardium, dense collagen, and adipose tissue, which can serve as a way to guide radiofrequency ablation therapy or endomyocardial biopsies. Using computer vision and machine learning, we present an automated algorithm to classify tissue compositions from cardiac optical coherence tomography (OCT) images. Three dimensional OCT volumes were obtained from 15 human hearts ex vivo within 48 hours of donor death (source, NDRI). We first segmented B-scans using a graph searching method. We estimated the boundary of each region by minimizing a cost function, which consisted of intensity, gradient, and contour smoothness. Then, features, including texture analysis, optical properties, and statistics of high moments, were extracted. We used a statistical model, relevance vector machine, and trained this model with abovementioned features to classify tissue compositions. To validate our method, we applied our algorithm to 77 volumes. The datasets for validation were manually segmented and classified by two investigators who were blind to our algorithm results and identified the tissues based on trichrome histology and pathology. The difference between automated and manual segmentation was 51.78 +/- 50.96 μm. Experiments showed that the attenuation coefficients of dense collagen were significantly different from other tissue types (P < 0.05, ANOVA). Importantly, myocardial fibrosis tissues were different from normal myocardium in entropy and kurtosis. The tissue types were classified with an accuracy of 84%. The results show good agreements with histology.

Texture segmentation by genetic programming.

PubMed

Song, Andy; Ciesielski, Vic

2008-01-01

This paper describes a texture segmentation method using genetic programming (GP), which is one of the most powerful evolutionary computation algorithms. By choosing an appropriate representation texture, classifiers can be evolved without computing texture features. Due to the absence of time-consuming feature extraction, the evolved classifiers enable the development of the proposed texture segmentation algorithm. This GP based method can achieve a segmentation speed that is significantly higher than that of conventional methods. This method does not require a human expert to manually construct models for texture feature extraction. In an analysis of the evolved classifiers, it can be seen that these GP classifiers are not arbitrary. Certain textural regularities are captured by these classifiers to discriminate different textures. GP has been shown in this study as a feasible and a powerful approach for texture classification and segmentation, which are generally considered as complex vision tasks.

Comparative Study of SVM Methods Combined with Voxel Selection for Object Category Classification on fMRI Data

PubMed Central

Song, Sutao; Zhan, Zhichao; Long, Zhiying; Zhang, Jiacai; Yao, Li

2011-01-01

Background Support vector machine (SVM) has been widely used as accurate and reliable method to decipher brain patterns from functional MRI (fMRI) data. Previous studies have not found a clear benefit for non-linear (polynomial kernel) SVM versus linear one. Here, a more effective non-linear SVM using radial basis function (RBF) kernel is compared with linear SVM. Different from traditional studies which focused either merely on the evaluation of different types of SVM or the voxel selection methods, we aimed to investigate the overall performance of linear and RBF SVM for fMRI classification together with voxel selection schemes on classification accuracy and time-consuming. Methodology/Principal Findings Six different voxel selection methods were employed to decide which voxels of fMRI data would be included in SVM classifiers with linear and RBF kernels in classifying 4-category objects. Then the overall performances of voxel selection and classification methods were compared. Results showed that: (1) Voxel selection had an important impact on the classification accuracy of the classifiers: in a relative low dimensional feature space, RBF SVM outperformed linear SVM significantly; in a relative high dimensional space, linear SVM performed better than its counterpart; (2) Considering the classification accuracy and time-consuming holistically, linear SVM with relative more voxels as features and RBF SVM with small set of voxels (after PCA) could achieve the better accuracy and cost shorter time. Conclusions/Significance The present work provides the first empirical result of linear and RBF SVM in classification of fMRI data, combined with voxel selection methods. Based on the findings, if only classification accuracy was concerned, RBF SVM with appropriate small voxels and linear SVM with relative more voxels were two suggested solutions; if users concerned more about the computational time, RBF SVM with relative small set of voxels when part of the principal components were kept as features was a better choice. PMID:21359184

Comparative study of SVM methods combined with voxel selection for object category classification on fMRI data.

PubMed

Song, Sutao; Zhan, Zhichao; Long, Zhiying; Zhang, Jiacai; Yao, Li

2011-02-16

Support vector machine (SVM) has been widely used as accurate and reliable method to decipher brain patterns from functional MRI (fMRI) data. Previous studies have not found a clear benefit for non-linear (polynomial kernel) SVM versus linear one. Here, a more effective non-linear SVM using radial basis function (RBF) kernel is compared with linear SVM. Different from traditional studies which focused either merely on the evaluation of different types of SVM or the voxel selection methods, we aimed to investigate the overall performance of linear and RBF SVM for fMRI classification together with voxel selection schemes on classification accuracy and time-consuming. Six different voxel selection methods were employed to decide which voxels of fMRI data would be included in SVM classifiers with linear and RBF kernels in classifying 4-category objects. Then the overall performances of voxel selection and classification methods were compared. Results showed that: (1) Voxel selection had an important impact on the classification accuracy of the classifiers: in a relative low dimensional feature space, RBF SVM outperformed linear SVM significantly; in a relative high dimensional space, linear SVM performed better than its counterpart; (2) Considering the classification accuracy and time-consuming holistically, linear SVM with relative more voxels as features and RBF SVM with small set of voxels (after PCA) could achieve the better accuracy and cost shorter time. The present work provides the first empirical result of linear and RBF SVM in classification of fMRI data, combined with voxel selection methods. Based on the findings, if only classification accuracy was concerned, RBF SVM with appropriate small voxels and linear SVM with relative more voxels were two suggested solutions; if users concerned more about the computational time, RBF SVM with relative small set of voxels when part of the principal components were kept as features was a better choice.

Applying a machine learning model using a locally preserving projection based feature regeneration algorithm to predict breast cancer risk

NASA Astrophysics Data System (ADS)

Heidari, Morteza; Zargari Khuzani, Abolfazl; Danala, Gopichandh; Mirniaharikandehei, Seyedehnafiseh; Qian, Wei; Zheng, Bin

2018-03-01

Both conventional and deep machine learning has been used to develop decision-support tools applied in medical imaging informatics. In order to take advantages of both conventional and deep learning approach, this study aims to investigate feasibility of applying a locally preserving projection (LPP) based feature regeneration algorithm to build a new machine learning classifier model to predict short-term breast cancer risk. First, a computer-aided image processing scheme was used to segment and quantify breast fibro-glandular tissue volume. Next, initially computed 44 image features related to the bilateral mammographic tissue density asymmetry were extracted. Then, an LLP-based feature combination method was applied to regenerate a new operational feature vector using a maximal variance approach. Last, a k-nearest neighborhood (KNN) algorithm based machine learning classifier using the LPP-generated new feature vectors was developed to predict breast cancer risk. A testing dataset involving negative mammograms acquired from 500 women was used. Among them, 250 were positive and 250 remained negative in the next subsequent mammography screening. Applying to this dataset, LLP-generated feature vector reduced the number of features from 44 to 4. Using a leave-onecase-out validation method, area under ROC curve produced by the KNN classifier significantly increased from 0.62 to 0.68 (p < 0.05) and odds ratio was 4.60 with a 95% confidence interval of [3.16, 6.70]. Study demonstrated that this new LPP-based feature regeneration approach enabled to produce an optimal feature vector and yield improved performance in assisting to predict risk of women having breast cancer detected in the next subsequent mammography screening.

Sparse representation of multi parametric DCE-MRI features using K-SVD for classifying gene expression based breast cancer recurrence risk

NASA Astrophysics Data System (ADS)

Mahrooghy, Majid; Ashraf, Ahmed B.; Daye, Dania; Mies, Carolyn; Rosen, Mark; Feldman, Michael; Kontos, Despina

2014-03-01

We evaluate the prognostic value of sparse representation-based features by applying the K-SVD algorithm on multiparametric kinetic, textural, and morphologic features in breast dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI). K-SVD is an iterative dimensionality reduction method that optimally reduces the initial feature space by updating the dictionary columns jointly with the sparse representation coefficients. Therefore, by using K-SVD, we not only provide sparse representation of the features and condense the information in a few coefficients but also we reduce the dimensionality. The extracted K-SVD features are evaluated by a machine learning algorithm including a logistic regression classifier for the task of classifying high versus low breast cancer recurrence risk as determined by a validated gene expression assay. The features are evaluated using ROC curve analysis and leave one-out cross validation for different sparse representation and dimensionality reduction numbers. Optimal sparse representation is obtained when the number of dictionary elements is 4 (K=4) and maximum non-zero coefficients is 2 (L=2). We compare K-SVD with ANOVA based feature selection for the same prognostic features. The ROC results show that the AUC of the K-SVD based (K=4, L=2), the ANOVA based, and the original features (i.e., no dimensionality reduction) are 0.78, 0.71. and 0.68, respectively. From the results, it can be inferred that by using sparse representation of the originally extracted multi-parametric, high-dimensional data, we can condense the information on a few coefficients with the highest predictive value. In addition, the dimensionality reduction introduced by K-SVD can prevent models from over-fitting.

Object-based Classification for Detecting Landslides and Stochastic Procedure to landslide susceptibility maps - A Case at Baolai Village, SW Taiwan

NASA Astrophysics Data System (ADS)

Lin, Ying-Tong; Chang, Kuo-Chen; Yang, Ci-Jian

2017-04-01

As the result of global warming in the past decades, Taiwan has experienced more and more extreme typhoons with hazardous massive landslides. In this study, we use object-oriented analysis method to classify landslide area at Baolai village by using Formosat-2 satellite images. We used for multiresolution segmented to generate the blocks, and used hierarchical logic to classified 5 different kinds of features. After that, classification the landslide into different type of landslide. Beside, we use stochastic procedure to integrate landslide susceptibility maps. This study assumed that in the extreme event, 2009 Typhoon Morakot, which precipitation goes to 1991.5mm in 5 days, and the highest landslide susceptible area. The results show that study area's landslide area was greatly changes, most of landslide was erosion by gully and made dip slope slide, or erosion by the stream, especially at undercut bank. From the landslide susceptibility maps, we know that the old landslide area have high potential to occur landslides in the extreme event. This study demonstrates the changing of landslide area and the landslide susceptible area. Keywords: Formosat-2, object-oriented, segmentation, classification, landslide, Baolai Village, SW Taiwan, FS

Building Change Detection from Bi-Temporal Dense-Matching Point Clouds and Aerial Images.

PubMed

Pang, Shiyan; Hu, Xiangyun; Cai, Zhongliang; Gong, Jinqi; Zhang, Mi

2018-03-24

In this work, a novel building change detection method from bi-temporal dense-matching point clouds and aerial images is proposed to address two major problems, namely, the robust acquisition of the changed objects above ground and the automatic classification of changed objects into buildings or non-buildings. For the acquisition of changed objects above ground, the change detection problem is converted into a binary classification, in which the changed area above ground is regarded as the foreground and the other area as the background. For the gridded points of each period, the graph cuts algorithm is adopted to classify the points into foreground and background, followed by the region-growing algorithm to form candidate changed building objects. A novel structural feature that was extracted from aerial images is constructed to classify the candidate changed building objects into buildings and non-buildings. The changed building objects are further classified as "newly built", "taller", "demolished", and "lower" by combining the classification and the digital surface models of two periods. Finally, three typical areas from a large dataset are used to validate the proposed method. Numerous experiments demonstrate the effectiveness of the proposed algorithm.

Classifier ensemble construction with rotation forest to improve medical diagnosis performance of machine learning algorithms.

PubMed

Ozcift, Akin; Gulten, Arif

2011-12-01

Improving accuracies of machine learning algorithms is vital in designing high performance computer-aided diagnosis (CADx) systems. Researches have shown that a base classifier performance might be enhanced by ensemble classification strategies. In this study, we construct rotation forest (RF) ensemble classifiers of 30 machine learning algorithms to evaluate their classification performances using Parkinson's, diabetes and heart diseases from literature. While making experiments, first the feature dimension of three datasets is reduced using correlation based feature selection (CFS) algorithm. Second, classification performances of 30 machine learning algorithms are calculated for three datasets. Third, 30 classifier ensembles are constructed based on RF algorithm to assess performances of respective classifiers with the same disease data. All the experiments are carried out with leave-one-out validation strategy and the performances of the 60 algorithms are evaluated using three metrics; classification accuracy (ACC), kappa error (KE) and area under the receiver operating characteristic (ROC) curve (AUC). Base classifiers succeeded 72.15%, 77.52% and 84.43% average accuracies for diabetes, heart and Parkinson's datasets, respectively. As for RF classifier ensembles, they produced average accuracies of 74.47%, 80.49% and 87.13% for respective diseases. RF, a newly proposed classifier ensemble algorithm, might be used to improve accuracy of miscellaneous machine learning algorithms to design advanced CADx systems. Copyright © 2011 Elsevier Ireland Ltd. All rights reserved.

Some new classification methods for hyperspectral remote sensing

NASA Astrophysics Data System (ADS)

Du, Pei-jun; Chen, Yun-hao; Jones, Simon; Ferwerda, Jelle G.; Chen, Zhi-jun; Zhang, Hua-peng; Tan, Kun; Yin, Zuo-xia

2006-10-01

Hyperspectral Remote Sensing (HRS) is one of the most significant recent achievements of Earth Observation Technology. Classification is the most commonly employed processing methodology. In this paper three new hyperspectral RS image classification methods are analyzed. These methods are: Object-oriented FIRS image classification, HRS image classification based on information fusion and HSRS image classification by Back Propagation Neural Network (BPNN). OMIS FIRS image is used as the example data. Object-oriented techniques have gained popularity for RS image classification in recent years. In such method, image segmentation is used to extract the regions from the pixel information based on homogeneity criteria at first, and spectral parameters like mean vector, texture, NDVI and spatial/shape parameters like aspect ratio, convexity, solidity, roundness and orientation for each region are calculated, finally classification of the image using the region feature vectors and also using suitable classifiers such as artificial neural network (ANN). It proves that object-oriented methods can improve classification accuracy since they utilize information and features both from the point and the neighborhood, and the processing unit is a polygon (in which all pixels are homogeneous and belong to the class). HRS image classification based on information fusion, divides all bands of the image into different groups initially, and extracts features from every group according to the properties of each group. Three levels of information fusion: data level fusion, feature level fusion and decision level fusion are used to HRS image classification. Artificial Neural Network (ANN) can perform well in RS image classification. In order to promote the advances of ANN used for HIRS image classification, Back Propagation Neural Network (BPNN), the most commonly used neural network, is used to HRS image classification.

A novel method for predicting kidney stone type using ensemble learning.

PubMed

Kazemi, Yassaman; Mirroshandel, Seyed Abolghasem

2018-01-01

The high morbidity rate associated with kidney stone disease, which is a silent killer, is one of the main concerns in healthcare systems all over the world. Advanced data mining techniques such as classification can help in the early prediction of this disease and reduce its incidence and associated costs. The objective of the present study is to derive a model for the early detection of the type of kidney stone and the most influential parameters with the aim of providing a decision-support system. Information was collected from 936 patients with nephrolithiasis at the kidney center of the Razi Hospital in Rasht from 2012 through 2016. The prepared dataset included 42 features. Data pre-processing was the first step toward extracting the relevant features. The collected data was analyzed with Weka software, and various data mining models were used to prepare a predictive model. Various data mining algorithms such as the Bayesian model, different types of Decision Trees, Artificial Neural Networks, and Rule-based classifiers were used in these models. We also proposed four models based on ensemble learning to improve the accuracy of each learning algorithm. In addition, a novel technique for combining individual classifiers in ensemble learning was proposed. In this technique, for each individual classifier, a weight is assigned based on our proposed genetic algorithm based method. The generated knowledge was evaluated using a 10-fold cross-validation technique based on standard measures. However, the assessment of each feature for building a predictive model was another significant challenge. The predictive strength of each feature for creating a reproducible outcome was also investigated. Regarding the applied models, parameters such as sex, acid uric condition, calcium level, hypertension, diabetes, nausea and vomiting, flank pain, and urinary tract infection (UTI) were the most vital parameters for predicting the chance of nephrolithiasis. The final ensemble-based model (with an accuracy of 97.1%) was a robust one and could be safely applied to future studies to predict the chances of developing nephrolithiasis. This model provides a novel way to study stone disease by deciphering the complex interaction among different biological variables, thus helping in an early identification and reduction in diagnosis time. Copyright © 2017 Elsevier B.V. All rights reserved.

Clinical application of modified bag-of-features coupled with hybrid neural-based classifier in dengue fever classification using gene expression data.

PubMed

Chatterjee, Sankhadeep; Dey, Nilanjan; Shi, Fuqian; Ashour, Amira S; Fong, Simon James; Sen, Soumya

2018-04-01

Dengue fever detection and classification have a vital role due to the recent outbreaks of different kinds of dengue fever. Recently, the advancement in the microarray technology can be employed for such classification process. Several studies have established that the gene selection phase takes a significant role in the classifier performance. Subsequently, the current study focused on detecting two different variations, namely, dengue fever (DF) and dengue hemorrhagic fever (DHF). A modified bag-of-features method has been proposed to select the most promising genes in the classification process. Afterward, a modified cuckoo search optimization algorithm has been engaged to support the artificial neural (ANN-MCS) to classify the unknown subjects into three different classes namely, DF, DHF, and another class containing convalescent and normal cases. The proposed method has been compared with other three well-known classifiers, namely, multilayer perceptron feed-forward network (MLP-FFN), artificial neural network (ANN) trained with cuckoo search (ANN-CS), and ANN trained with PSO (ANN-PSO). Experiments have been carried out with different number of clusters for the initial bag-of-features-based feature selection phase. After obtaining the reduced dataset, the hybrid ANN-MCS model has been employed for the classification process. The results have been compared in terms of the confusion matrix-based performance measuring metrics. The experimental results indicated a highly statistically significant improvement with the proposed classifier over the traditional ANN-CS model.

Finger vein identification using fuzzy-based k-nearest centroid neighbor classifier

NASA Astrophysics Data System (ADS)

Rosdi, Bakhtiar Affendi; Jaafar, Haryati; Ramli, Dzati Athiar

2015-02-01

In this paper, a new approach for personal identification using finger vein image is presented. Finger vein is an emerging type of biometrics that attracts attention of researchers in biometrics area. As compared to other biometric traits such as face, fingerprint and iris, finger vein is more secured and hard to counterfeit since the features are inside the human body. So far, most of the researchers focus on how to extract robust features from the captured vein images. Not much research was conducted on the classification of the extracted features. In this paper, a new classifier called fuzzy-based k-nearest centroid neighbor (FkNCN) is applied to classify the finger vein image. The proposed FkNCN employs a surrounding rule to obtain the k-nearest centroid neighbors based on the spatial distributions of the training images and their distance to the test image. Then, the fuzzy membership function is utilized to assign the test image to the class which is frequently represented by the k-nearest centroid neighbors. Experimental evaluation using our own database which was collected from 492 fingers shows that the proposed FkNCN has better performance than the k-nearest neighbor, k-nearest-centroid neighbor and fuzzy-based-k-nearest neighbor classifiers. This shows that the proposed classifier is able to identify the finger vein image effectively.

Fourier transform infrared spectroscopy microscopic imaging classification based on spatial-spectral features

NASA Astrophysics Data System (ADS)

Liu, Lian; Yang, Xiukun; Zhong, Mingliang; Liu, Yao; Jing, Xiaojun; Yang, Qin

2018-04-01

The discrete fractional Brownian incremental random (DFBIR) field is used to describe the irregular, random, and highly complex shapes of natural objects such as coastlines and biological tissues, for which traditional Euclidean geometry cannot be used. In this paper, an anisotropic variable window (AVW) directional operator based on the DFBIR field model is proposed for extracting spatial characteristics of Fourier transform infrared spectroscopy (FTIR) microscopic imaging. Probabilistic principal component analysis first extracts spectral features, and then the spatial features of the proposed AVW directional operator are combined with the former to construct a spatial-spectral structure, which increases feature-related information and helps a support vector machine classifier to obtain more efficient distribution-related information. Compared to Haralick’s grey-level co-occurrence matrix, Gabor filters, and local binary patterns (e.g. uniform LBPs, rotation-invariant LBPs, uniform rotation-invariant LBPs), experiments on three FTIR spectroscopy microscopic imaging datasets show that the proposed AVW directional operator is more advantageous in terms of classification accuracy, particularly for low-dimensional spaces of spatial characteristics.

Classification method, spectral diversity, band combination and accuracy assessment evaluation for urban feature detection

NASA Astrophysics Data System (ADS)

Erener, A.

2013-04-01

Automatic extraction of urban features from high resolution satellite images is one of the main applications in remote sensing. It is useful for wide scale applications, namely: urban planning, urban mapping, disaster management, GIS (geographic information systems) updating, and military target detection. One common approach to detecting urban features from high resolution images is to use automatic classification methods. This paper has four main objectives with respect to detecting buildings. The first objective is to compare the performance of the most notable supervised classification algorithms, including the maximum likelihood classifier (MLC) and the support vector machine (SVM). In this experiment the primary consideration is the impact of kernel configuration on the performance of the SVM. The second objective of the study is to explore the suitability of integrating additional bands, namely first principal component (1st PC) and the intensity image, for original data for multi classification approaches. The performance evaluation of classification results is done using two different accuracy assessment methods: pixel based and object based approaches, which reflect the third aim of the study. The objective here is to demonstrate the differences in the evaluation of accuracies of classification methods. Considering consistency, the same set of ground truth data which is produced by labeling the building boundaries in the GIS environment is used for accuracy assessment. Lastly, the fourth aim is to experimentally evaluate variation in the accuracy of classifiers for six different real situations in order to identify the impact of spatial and spectral diversity on results. The method is applied to Quickbird images for various urban complexity levels, extending from simple to complex urban patterns. The simple surface type includes a regular urban area with low density and systematic buildings with brick rooftops. The complex surface type involves almost all kinds of challenges, such as high dense build up areas, regions with bare soil, and small and large buildings with different rooftops, such as concrete, brick, and metal. Using the pixel based accuracy assessment it was shown that the percent building detection (PBD) and quality percent (QP) of the MLC and SVM depend on the complexity and texture variation of the region. Generally, PBD values range between 70% and 90% for the MLC and SVM, respectively. No substantial improvements were observed when the SVM and MLC classifications were developed by the addition of more variables, instead of the use of only four bands. In the evaluation of object based accuracy assessment, it was demonstrated that while MLC and SVM provide higher rates of correct detection, they also provide higher rates of false alarms.

MultiMiTar: a novel multi objective optimization based miRNA-target prediction method.

PubMed

Mitra, Ramkrishna; Bandyopadhyay, Sanghamitra

2011-01-01

Machine learning based miRNA-target prediction algorithms often fail to obtain a balanced prediction accuracy in terms of both sensitivity and specificity due to lack of the gold standard of negative examples, miRNA-targeting site context specific relevant features and efficient feature selection process. Moreover, all the sequence, structure and machine learning based algorithms are unable to distribute the true positive predictions preferentially at the top of the ranked list; hence the algorithms become unreliable to the biologists. In addition, these algorithms fail to obtain considerable combination of precision and recall for the target transcripts that are translationally repressed at protein level. In the proposed article, we introduce an efficient miRNA-target prediction system MultiMiTar, a Support Vector Machine (SVM) based classifier integrated with a multiobjective metaheuristic based feature selection technique. The robust performance of the proposed method is mainly the result of using high quality negative examples and selection of biologically relevant miRNA-targeting site context specific features. The features are selected by using a novel feature selection technique AMOSA-SVM, that integrates the multi objective optimization technique Archived Multi-Objective Simulated Annealing (AMOSA) and SVM. MultiMiTar is found to achieve much higher Matthew's correlation coefficient (MCC) of 0.583 and average class-wise accuracy (ACA) of 0.8 compared to the others target prediction methods for a completely independent test data set. The obtained MCC and ACA values of these algorithms range from -0.269 to 0.155 and 0.321 to 0.582, respectively. Moreover, it shows a more balanced result in terms of precision and sensitivity (recall) for the translationally repressed data set as compared to all the other existing methods. An important aspect is that the true positive predictions are distributed preferentially at the top of the ranked list that makes MultiMiTar reliable for the biologists. MultiMiTar is now available as an online tool at www.isical.ac.in/~bioinfo_miu/multimitar.htm. MultiMiTar software can be downloaded from www.isical.ac.in/~bioinfo_miu/multimitar-download.htm.

Deep convolutional neural network processing of aerial stereo imagery to monitor vulnerable zones near power lines

NASA Astrophysics Data System (ADS)

Qayyum, Abdul; Saad, Naufal M.; Kamel, Nidal; Malik, Aamir Saeed

2018-01-01

The monitoring of vegetation near high-voltage transmission power lines and poles is tedious. Blackouts present a huge challenge to power distribution companies and often occur due to tree growth in hilly and rural areas. There are numerous methods of monitoring hazardous overgrowth that are expensive and time-consuming. Accurate estimation of tree and vegetation heights near power poles can prevent the disruption of power transmission in vulnerable zones. This paper presents a cost-effective approach based on a convolutional neural network (CNN) algorithm to compute the height (depth maps) of objects proximal to power poles and transmission lines. The proposed CNN extracts and classifies features by employing convolutional pooling inputs to fully connected data layers that capture prominent features from stereo image patches. Unmanned aerial vehicle or satellite stereo image datasets can thus provide a feasible and cost-effective approach that identifies threat levels based on height and distance estimations of hazardous vegetation and other objects. Results were compared with extant disparity map estimation techniques, such as graph cut, dynamic programming, belief propagation, and area-based methods. The proposed method achieved an accuracy rate of 90%.

Face recognition system using multiple face model of hybrid Fourier feature under uncontrolled illumination variation.

PubMed

Hwang, Wonjun; Wang, Haitao; Kim, Hyunwoo; Kee, Seok-Cheol; Kim, Junmo

2011-04-01

The authors present a robust face recognition system for large-scale data sets taken under uncontrolled illumination variations. The proposed face recognition system consists of a novel illumination-insensitive preprocessing method, a hybrid Fourier-based facial feature extraction, and a score fusion scheme. First, in the preprocessing stage, a face image is transformed into an illumination-insensitive image, called an "integral normalized gradient image," by normalizing and integrating the smoothed gradients of a facial image. Then, for feature extraction of complementary classifiers, multiple face models based upon hybrid Fourier features are applied. The hybrid Fourier features are extracted from different Fourier domains in different frequency bandwidths, and then each feature is individually classified by linear discriminant analysis. In addition, multiple face models are generated by plural normalized face images that have different eye distances. Finally, to combine scores from multiple complementary classifiers, a log likelihood ratio-based score fusion scheme is applied. The proposed system using the face recognition grand challenge (FRGC) experimental protocols is evaluated; FRGC is a large available data set. Experimental results on the FRGC version 2.0 data sets have shown that the proposed method shows an average of 81.49% verification rate on 2-D face images under various environmental variations such as illumination changes, expression changes, and time elapses.

a Fully Automated Pipeline for Classification Tasks with AN Application to Remote Sensing

NASA Astrophysics Data System (ADS)

Suzuki, K.; Claesen, M.; Takeda, H.; De Moor, B.

2016-06-01

Nowadays deep learning has been intensively in spotlight owing to its great victories at major competitions, which undeservedly pushed `shallow' machine learning methods, relatively naive/handy algorithms commonly used by industrial engineers, to the background in spite of their facilities such as small requisite amount of time/dataset for training. We, with a practical point of view, utilized shallow learning algorithms to construct a learning pipeline such that operators can utilize machine learning without any special knowledge, expensive computation environment, and a large amount of labelled data. The proposed pipeline automates a whole classification process, namely feature-selection, weighting features and the selection of the most suitable classifier with optimized hyperparameters. The configuration facilitates particle swarm optimization, one of well-known metaheuristic algorithms for the sake of generally fast and fine optimization, which enables us not only to optimize (hyper)parameters but also to determine appropriate features/classifier to the problem, which has conventionally been a priori based on domain knowledge and remained untouched or dealt with naïve algorithms such as grid search. Through experiments with the MNIST and CIFAR-10 datasets, common datasets in computer vision field for character recognition and object recognition problems respectively, our automated learning approach provides high performance considering its simple setting (i.e. non-specialized setting depending on dataset), small amount of training data, and practical learning time. Moreover, compared to deep learning the performance stays robust without almost any modification even with a remote sensing object recognition problem, which in turn indicates that there is a high possibility that our approach contributes to general classification problems.

Classification of Urban Aerial Data Based on Pixel Labelling with Deep Convolutional Neural Networks and Logistic Regression

NASA Astrophysics Data System (ADS)

Yao, W.; Poleswki, P.; Krzystek, P.

2016-06-01

The recent success of deep convolutional neural networks (CNN) on a large number of applications can be attributed to large amounts of available training data and increasing computing power. In this paper, a semantic pixel labelling scheme for urban areas using multi-resolution CNN and hand-crafted spatial-spectral features of airborne remotely sensed data is presented. Both CNN and hand-crafted features are applied to image/DSM patches to produce per-pixel class probabilities with a L1-norm regularized logistical regression classifier. The evidence theory infers a degree of belief for pixel labelling from different sources to smooth regions by handling the conflicts present in the both classifiers while reducing the uncertainty. The aerial data used in this study were provided by ISPRS as benchmark datasets for 2D semantic labelling tasks in urban areas, which consists of two data sources from LiDAR and color infrared camera. The test sites are parts of a city in Germany which is assumed to consist of typical object classes including impervious surfaces, trees, buildings, low vegetation, vehicles and clutter. The evaluation is based on the computation of pixel-based confusion matrices by random sampling. The performance of the strategy with respect to scene characteristics and method combination strategies is analyzed and discussed. The competitive classification accuracy could be not only explained by the nature of input data sources: e.g. the above-ground height of nDSM highlight the vertical dimension of houses, trees even cars and the nearinfrared spectrum indicates vegetation, but also attributed to decision-level fusion of CNN's texture-based approach with multichannel spatial-spectral hand-crafted features based on the evidence combination theory.

[Object-oriented segmentation and classification of forest gap based on QuickBird remote sensing image.

PubMed

Mao, Xue Gang; Du, Zi Han; Liu, Jia Qian; Chen, Shu Xin; Hou, Ji Yu

2018-01-01

Traditional field investigation and artificial interpretation could not satisfy the need of forest gaps extraction at regional scale. High spatial resolution remote sensing image provides the possibility for regional forest gaps extraction. In this study, we used object-oriented classification method to segment and classify forest gaps based on QuickBird high resolution optical remote sensing image in Jiangle National Forestry Farm of Fujian Province. In the process of object-oriented classification, 10 scales (10-100, with a step length of 10) were adopted to segment QuickBird remote sensing image; and the intersection area of reference object (RA or ) and intersection area of segmented object (RA os ) were adopted to evaluate the segmentation result at each scale. For segmentation result at each scale, 16 spectral characteristics and support vector machine classifier (SVM) were further used to classify forest gaps, non-forest gaps and others. The results showed that the optimal segmentation scale was 40 when RA or was equal to RA os . The accuracy difference between the maximum and minimum at different segmentation scales was 22%. At optimal scale, the overall classification accuracy was 88% (Kappa=0.82) based on SVM classifier. Combining high resolution remote sensing image data with object-oriented classification method could replace the traditional field investigation and artificial interpretation method to identify and classify forest gaps at regional scale.

A Comparison of Physiological Signal Analysis Techniques and Classifiers for Automatic Emotional Evaluation of Audiovisual Contents

PubMed Central

Colomer Granero, Adrián; Fuentes-Hurtado, Félix; Naranjo Ornedo, Valery; Guixeres Provinciale, Jaime; Ausín, Jose M.; Alcañiz Raya, Mariano

2016-01-01

This work focuses on finding the most discriminatory or representative features that allow to classify commercials according to negative, neutral and positive effectiveness based on the Ace Score index. For this purpose, an experiment involving forty-seven participants was carried out. In this experiment electroencephalography (EEG), electrocardiography (ECG), Galvanic Skin Response (GSR) and respiration data were acquired while subjects were watching a 30-min audiovisual content. This content was composed by a submarine documentary and nine commercials (one of them the ad under evaluation). After the signal pre-processing, four sets of features were extracted from the physiological signals using different state-of-the-art metrics. These features computed in time and frequency domains are the inputs to several basic and advanced classifiers. An average of 89.76% of the instances was correctly classified according to the Ace Score index. The best results were obtained by a classifier consisting of a combination between AdaBoost and Random Forest with automatic selection of features. The selected features were those extracted from GSR and HRV signals. These results are promising in the audiovisual content evaluation field by means of physiological signal processing. PMID:27471462

A Comparison of Physiological Signal Analysis Techniques and Classifiers for Automatic Emotional Evaluation of Audiovisual Contents.

PubMed

Colomer Granero, Adrián; Fuentes-Hurtado, Félix; Naranjo Ornedo, Valery; Guixeres Provinciale, Jaime; Ausín, Jose M; Alcañiz Raya, Mariano

2016-01-01

This work focuses on finding the most discriminatory or representative features that allow to classify commercials according to negative, neutral and positive effectiveness based on the Ace Score index. For this purpose, an experiment involving forty-seven participants was carried out. In this experiment electroencephalography (EEG), electrocardiography (ECG), Galvanic Skin Response (GSR) and respiration data were acquired while subjects were watching a 30-min audiovisual content. This content was composed by a submarine documentary and nine commercials (one of them the ad under evaluation). After the signal pre-processing, four sets of features were extracted from the physiological signals using different state-of-the-art metrics. These features computed in time and frequency domains are the inputs to several basic and advanced classifiers. An average of 89.76% of the instances was correctly classified according to the Ace Score index. The best results were obtained by a classifier consisting of a combination between AdaBoost and Random Forest with automatic selection of features. The selected features were those extracted from GSR and HRV signals. These results are promising in the audiovisual content evaluation field by means of physiological signal processing.

Category Learning Research in the Interactive Online Environment Second Life

NASA Technical Reports Server (NTRS)

Andrews, Jan; Livingston, Ken; Sturm, Joshua; Bliss, Daniel; Hawthorne, Daniel

2011-01-01

The interactive online environment Second Life allows users to create novel three-dimensional stimuli that can be manipulated in a meaningful yet controlled environment. These features suggest Second Life's utility as a powerful tool for investigating how people learn concepts for unfamiliar objects. The first of two studies was designed to establish that cognitive processes elicited in this virtual world are comparable to those tapped in conventional settings by attempting to replicate the established finding that category learning systematically influences perceived similarity . From the perspective of an avatar, participants navigated a course of unfamiliar three-dimensional stimuli and were trained to classify them into two labeled categories based on two visual features. Participants then gave similarity ratings for pairs of stimuli and their responses were compared to those of control participants who did not learn the categories. Results indicated significant compression, whereby objects classified together were judged to be more similar by learning than control participants, thus supporting the validity of using Second Life as a laboratory for studying human cognition. A second study used Second Life to test the novel hypothesis that effects of learning on perceived similarity do not depend on the presence of verbal labels for categories. We presented the same stimuli but participants classified them by selecting between two complex visual patterns designed to be extremely difficult to label. While learning was more challenging in this condition , those who did learn without labels showed a compression effect identical to that found in the first study using verbal labels. Together these studies establish that at least some forms of human learning in Second Life parallel learning in the actual world and thus open the door to future studies that will make greater use of the enriched variety of objects and interactions possible in simulated environments compared to traditional experimental situations.

A hybrid three-class brain-computer interface system utilizing SSSEPs and transient ERPs

NASA Astrophysics Data System (ADS)

Breitwieser, Christian; Pokorny, Christoph; Müller-Putz, Gernot R.

2016-12-01

Objective. This paper investigates the fusion of steady-state somatosensory evoked potentials (SSSEPs) and transient event-related potentials (tERPs), evoked through tactile simulation on the left and right-hand fingertips, in a three-class EEG based hybrid brain-computer interface. It was hypothesized, that fusing the input signals leads to higher classification rates than classifying tERP and SSSEP individually. Approach. Fourteen subjects participated in the studies, consisting of a screening paradigm to determine person dependent resonance-like frequencies and a subsequent online paradigm. The whole setup of the BCI system was based on open interfaces, following suggestions for a common implementation platform. During the online experiment, subjects were instructed to focus their attention on the stimulated fingertips as indicated by a visual cue. The recorded data were classified during runtime using a multi-class shrinkage LDA classifier and the outputs were fused together applying a posterior probability based fusion. Data were further analyzed offline, involving a combined classification of SSSEP and tERP features as a second fusion principle. The final results were tested for statistical significance applying a repeated measures ANOVA. Main results. A significant classification increase was achieved when fusing the results with a combined classification compared to performing an individual classification. Furthermore, the SSSEP classifier was significantly better in detecting a non-control state, whereas the tERP classifier was significantly better in detecting control states. Subjects who had a higher relative band power increase during the screening session also achieved significantly higher classification results than subjects with lower relative band power increase. Significance. It could be shown that utilizing SSSEP and tERP for hBCIs increases the classification accuracy and also that tERP and SSSEP are not classifying control- and non-control states with the same level of accuracy.

Circular blurred shape model for multiclass symbol recognition.

PubMed

Escalera, Sergio; Fornés, Alicia; Pujol, Oriol; Lladós, Josep; Radeva, Petia

2011-04-01

In this paper, we propose a circular blurred shape model descriptor to deal with the problem of symbol detection and classification as a particular case of object recognition. The feature extraction is performed by capturing the spatial arrangement of significant object characteristics in a correlogram structure. The shape information from objects is shared among correlogram regions, where a prior blurring degree defines the level of distortion allowed in the symbol, making the descriptor tolerant to irregular deformations. Moreover, the descriptor is rotation invariant by definition. We validate the effectiveness of the proposed descriptor in both the multiclass symbol recognition and symbol detection domains. In order to perform the symbol detection, the descriptors are learned using a cascade of classifiers. In the case of multiclass categorization, the new feature space is learned using a set of binary classifiers which are embedded in an error-correcting output code design. The results over four symbol data sets show the significant improvements of the proposed descriptor compared to the state-of-the-art descriptors. In particular, the results are even more significant in those cases where the symbols suffer from elastic deformations.

Classifying MCI Subtypes in Community-Dwelling Elderly Using Cross-Sectional and Longitudinal MRI-Based Biomarkers

PubMed Central

Guan, Hao; Liu, Tao; Jiang, Jiyang; Tao, Dacheng; Zhang, Jicong; Niu, Haijun; Zhu, Wanlin; Wang, Yilong; Cheng, Jian; Kochan, Nicole A.; Brodaty, Henry; Sachdev, Perminder; Wen, Wei

2017-01-01

Amnestic MCI (aMCI) and non-amnestic MCI (naMCI) are considered to differ in etiology and outcome. Accurately classifying MCI into meaningful subtypes would enable early intervention with targeted treatment. In this study, we employed structural magnetic resonance imaging (MRI) for MCI subtype classification. This was carried out in a sample of 184 community-dwelling individuals (aged 73–85 years). Cortical surface based measurements were computed from longitudinal and cross-sectional scans. By introducing a feature selection algorithm, we identified a set of discriminative features, and further investigated the temporal patterns of these features. A voting classifier was trained and evaluated via 10 iterations of cross-validation. The best classification accuracies achieved were: 77% (naMCI vs. aMCI), 81% (aMCI vs. cognitively normal (CN)) and 70% (naMCI vs. CN). The best results for differentiating aMCI from naMCI were achieved with baseline features. Hippocampus, amygdala and frontal pole were found to be most discriminative for classifying MCI subtypes. Additionally, we observed the dynamics of classification of several MRI biomarkers. Learning the dynamics of atrophy may aid in the development of better biomarkers, as it may track the progression of cognitive impairment. PMID:29085292

Identifying sports videos using replay, text, and camera motion features

NASA Astrophysics Data System (ADS)

Kobla, Vikrant; DeMenthon, Daniel; Doermann, David S.

1999-12-01

Automated classification of digital video is emerging as an important piece of the puzzle in the design of content management systems for digital libraries. The ability to classify videos into various classes such as sports, news, movies, or documentaries, increases the efficiency of indexing, browsing, and retrieval of video in large databases. In this paper, we discuss the extraction of features that enable identification of sports videos directly from the compressed domain of MPEG video. These features include detecting the presence of action replays, determining the amount of scene text in vide, and calculating various statistics on camera and/or object motion. The features are derived from the macroblock, motion,and bit-rate information that is readily accessible from MPEG video with very minimal decoding, leading to substantial gains in processing speeds. Full-decoding of selective frames is required only for text analysis. A decision tree classifier built using these features is able to identify sports clips with an accuracy of about 93 percent.

DOE Office of Scientific and Technical Information (OSTI.GOV)

Islam, Md. Shafiqul, E-mail: shafique@eng.ukm.my; Hannan, M.A., E-mail: hannan@eng.ukm.my; Basri, Hassan

Highlights: • Solid waste bin level detection using Dynamic Time Warping (DTW). • Gabor wavelet filter is used to extract the solid waste image features. • Multi-Layer Perceptron classifier network is used for bin image classification. • The classification performance evaluated by ROC curve analysis. - Abstract: The increasing requirement for Solid Waste Management (SWM) has become a significant challenge for municipal authorities. A number of integrated systems and methods have introduced to overcome this challenge. Many researchers have aimed to develop an ideal SWM system, including approaches involving software-based routing, Geographic Information Systems (GIS), Radio-frequency Identification (RFID), or sensormore » intelligent bins. Image processing solutions for the Solid Waste (SW) collection have also been developed; however, during capturing the bin image, it is challenging to position the camera for getting a bin area centralized image. As yet, there is no ideal system which can correctly estimate the amount of SW. This paper briefly discusses an efficient image processing solution to overcome these problems. Dynamic Time Warping (DTW) was used for detecting and cropping the bin area and Gabor wavelet (GW) was introduced for feature extraction of the waste bin image. Image features were used to train the classifier. A Multi-Layer Perceptron (MLP) classifier was used to classify the waste bin level and estimate the amount of waste inside the bin. The area under the Receiver Operating Characteristic (ROC) curves was used to statistically evaluate classifier performance. The results of this developed system are comparable to previous image processing based system. The system demonstration using DTW with GW for feature extraction and an MLP classifier led to promising results with respect to the accuracy of waste level estimation (98.50%). The application can be used to optimize the routing of waste collection based on the estimated bin level.« less

Case base classification on digital mammograms: improving the performance of case base classifier

NASA Astrophysics Data System (ADS)

Raman, Valliappan; Then, H. H.; Sumari, Putra; Venkatesa Mohan, N.

2011-10-01

Breast cancer continues to be a significant public health problem in the world. Early detection is the key for improving breast cancer prognosis. The aim of the research presented here is in twofold. First stage of research involves machine learning techniques, which segments and extracts features from the mass of digital mammograms. Second level is on problem solving approach which includes classification of mass by performance based case base classifier. In this paper we build a case-based Classifier in order to diagnose mammographic images. We explain different methods and behaviors that have been added to the classifier to improve the performance of the classifier. Currently the initial Performance base Classifier with Bagging is proposed in the paper and it's been implemented and it shows an improvement in specificity and sensitivity.

Emotion detection model of Filipino music

NASA Astrophysics Data System (ADS)

Noblejas, Kathleen Alexis; Isidro, Daryl Arvin; Samonte, Mary Jane C.

2017-02-01

This research explored the creation of a model to detect emotion from Filipino songs. The emotion model used was based from Paul Ekman's six basic emotions. The songs were classified into the following genres: kundiman, novelty, pop, and rock. The songs were annotated by a group of music experts based on the emotion the song induces to the listener. Musical features of the songs were extracted using jAudio while the lyric features were extracted by Bag-of- Words feature representation. The audio and lyric features of the Filipino songs were extracted for classification by the chosen three classifiers, Naïve Bayes, Support Vector Machines, and k-Nearest Neighbors. The goal of the research was to know which classifier would work best for Filipino music. Evaluation was done by 10-fold cross validation and accuracy, precision, recall, and F-measure results were compared. Models were also tested with unknown test data to further determine the models' accuracy through the prediction results.

Lidar detection of underwater objects using a neuro-SVM-based architecture.

PubMed

Mitra, Vikramjit; Wang, Chia-Jiu; Banerjee, Satarupa

2006-05-01

This paper presents a neural network architecture using a support vector machine (SVM) as an inference engine (IE) for classification of light detection and ranging (Lidar) data. Lidar data gives a sequence of laser backscatter intensities obtained from laser shots generated from an airborne object at various altitudes above the earth surface. Lidar data is pre-filtered to remove high frequency noise. As the Lidar shots are taken from above the earth surface, it has some air backscatter information, which is of no importance for detecting underwater objects. Because of these, the air backscatter information is eliminated from the data and a segment of this data is subsequently selected to extract features for classification. This is then encoded using linear predictive coding (LPC) and polynomial approximation. The coefficients thus generated are used as inputs to the two branches of a parallel neural architecture. The decisions obtained from the two branches are vector multiplied and the result is fed to an SVM-based IE that presents the final inference. Two parallel neural architectures using multilayer perception (MLP) and hybrid radial basis function (HRBF) are considered in this paper. The proposed structure fits the Lidar data classification task well due to the inherent classification efficiency of neural networks and accurate decision-making capability of SVM. A Bayesian classifier and a quadratic classifier were considered for the Lidar data classification task but they failed to offer high prediction accuracy. Furthermore, a single-layered artificial neural network (ANN) classifier was also considered and it failed to offer good accuracy. The parallel ANN architecture proposed in this paper offers high prediction accuracy (98.9%) and is found to be the most suitable architecture for the proposed task of Lidar data classification.

A review and experimental study on the application of classifiers and evolutionary algorithms in EEG-based brain-machine interface systems

NASA Astrophysics Data System (ADS)

Tahernezhad-Javazm, Farajollah; Azimirad, Vahid; Shoaran, Maryam

2018-04-01

Objective. Considering the importance and the near-future development of noninvasive brain-machine interface (BMI) systems, this paper presents a comprehensive theoretical-experimental survey on the classification and evolutionary methods for BMI-based systems in which EEG signals are used. Approach. The paper is divided into two main parts. In the first part, a wide range of different types of the base and combinatorial classifiers including boosting and bagging classifiers and evolutionary algorithms are reviewed and investigated. In the second part, these classifiers and evolutionary algorithms are assessed and compared based on two types of relatively widely used BMI systems, sensory motor rhythm-BMI and event-related potentials-BMI. Moreover, in the second part, some of the improved evolutionary algorithms as well as bi-objective algorithms are experimentally assessed and compared. Main results. In this study two databases are used, and cross-validation accuracy (CVA) and stability to data volume (SDV) are considered as the evaluation criteria for the classifiers. According to the experimental results on both databases, regarding the base classifiers, linear discriminant analysis and support vector machines with respect to CVA evaluation metric, and naive Bayes with respect to SDV demonstrated the best performances. Among the combinatorial classifiers, four classifiers, Bagg-DT (bagging decision tree), LogitBoost, and GentleBoost with respect to CVA, and Bagging-LR (bagging logistic regression) and AdaBoost (adaptive boosting) with respect to SDV had the best performances. Finally, regarding the evolutionary algorithms, single-objective invasive weed optimization (IWO) and bi-objective nondominated sorting IWO algorithms demonstrated the best performances. Significance. We present a general survey on the base and the combinatorial classification methods for EEG signals (sensory motor rhythm and event-related potentials) as well as their optimization methods through the evolutionary algorithms. In addition, experimental and statistical significance tests are carried out to study the applicability and effectiveness of the reviewed methods.

Application of a neural network for reflectance spectrum classification

NASA Astrophysics Data System (ADS)

Yang, Gefei; Gartley, Michael

2017-05-01

Traditional reflectance spectrum classification algorithms are based on comparing spectrum across the electromagnetic spectrum anywhere from the ultra-violet to the thermal infrared regions. These methods analyze reflectance on a pixel by pixel basis. Inspired by high performance that Convolution Neural Networks (CNN) have demonstrated in image classification, we applied a neural network to analyze directional reflectance pattern images. By using the bidirectional reflectance distribution function (BRDF) data, we can reformulate the 4-dimensional into 2 dimensions, namely incident direction × reflected direction × channels. Meanwhile, RIT's micro-DIRSIG model is utilized to simulate additional training samples for improving the robustness of the neural networks training. Unlike traditional classification by using hand-designed feature extraction with a trainable classifier, neural networks create several layers to learn a feature hierarchy from pixels to classifier and all layers are trained jointly. Hence, the our approach of utilizing the angular features are different to traditional methods utilizing spatial features. Although training processing typically has a large computational cost, simple classifiers work well when subsequently using neural network generated features. Currently, most popular neural networks such as VGG, GoogLeNet and AlexNet are trained based on RGB spatial image data. Our approach aims to build a directional reflectance spectrum based neural network to help us to understand from another perspective. At the end of this paper, we compare the difference among several classifiers and analyze the trade-off among neural networks parameters.

Moving object localization using optical flow for pedestrian detection from a moving vehicle.

PubMed

Hariyono, Joko; Hoang, Van-Dung; Jo, Kang-Hyun

2014-01-01

This paper presents a pedestrian detection method from a moving vehicle using optical flows and histogram of oriented gradients (HOG). A moving object is extracted from the relative motion by segmenting the region representing the same optical flows after compensating the egomotion of the camera. To obtain the optical flow, two consecutive images are divided into grid cells 14 × 14 pixels; then each cell is tracked in the current frame to find corresponding cell in the next frame. Using at least three corresponding cells, affine transformation is performed according to each corresponding cell in the consecutive images, so that conformed optical flows are extracted. The regions of moving object are detected as transformed objects, which are different from the previously registered background. Morphological process is applied to get the candidate human regions. In order to recognize the object, the HOG features are extracted on the candidate region and classified using linear support vector machine (SVM). The HOG feature vectors are used as input of linear SVM to classify the given input into pedestrian/nonpedestrian. The proposed method was tested in a moving vehicle and also confirmed through experiments using pedestrian dataset. It shows a significant improvement compared with original HOG using ETHZ pedestrian dataset.

Optimization of Adaboost Algorithm for Sonar Target Detection in a Multi-Stage ATR System

NASA Technical Reports Server (NTRS)

Lin, Tsung Han (Hank)

2011-01-01

JPL has developed a multi-stage Automated Target Recognition (ATR) system to locate objects in images. First, input images are preprocessed and sent to a Grayscale Optical Correlator (GOC) filter to identify possible regions-of-interest (ROIs). Second, feature extraction operations are performed using Texton filters and Principal Component Analysis (PCA). Finally, the features are fed to a classifier, to identify ROIs that contain the targets. Previous work used the Feed-forward Back-propagation Neural Network for classification. In this project we investigate a version of Adaboost as a classifier for comparison. The version we used is known as GentleBoost. We used the boosted decision tree as the weak classifier. We have tested our ATR system against real-world sonar images using the Adaboost approach. Results indicate an improvement in performance over a single Neural Network design.

Classification of Urban Feature from Unmanned Aerial Vehicle Images Using Gasvm Integration and Multi-Scale Segmentation

NASA Astrophysics Data System (ADS)

Modiri, M.; Salehabadi, A.; Mohebbi, M.; Hashemi, A. M.; Masumi, M.

2015-12-01

The use of UAV in the application of photogrammetry to obtain cover images and achieve the main objectives of the photogrammetric mapping has been a boom in the region. The images taken from REGGIOLO region in the province of, Italy Reggio -Emilia by UAV with non-metric camera Canon Ixus and with an average height of 139.42 meters were used to classify urban feature. Using the software provided SURE and cover images of the study area, to produce dense point cloud, DSM and Artvqvtv spatial resolution of 10 cm was prepared. DTM area using Adaptive TIN filtering algorithm was developed. NDSM area was prepared with using the difference between DSM and DTM and a separate features in the image stack. In order to extract features, using simultaneous occurrence matrix features mean, variance, homogeneity, contrast, dissimilarity, entropy, second moment, and correlation for each of the RGB band image was used Orthophoto area. Classes used to classify urban problems, including buildings, trees and tall vegetation, grass and vegetation short, paved road and is impervious surfaces. Class consists of impervious surfaces such as pavement conditions, the cement, the car, the roof is stored. In order to pixel-based classification and selection of optimal features of classification was GASVM pixel basis. In order to achieve the classification results with higher accuracy and spectral composition informations, texture, and shape conceptual image featureOrthophoto area was fencing. The segmentation of multi-scale segmentation method was used.it belonged class. Search results using the proposed classification of urban feature, suggests the suitability of this method of classification complications UAV is a city using images. The overall accuracy and kappa coefficient method proposed in this study, respectively, 47/93% and 84/91% was.

Non-proliferative diabetic retinopathy symptoms detection and classification using neural network.

PubMed

Al-Jarrah, Mohammad A; Shatnawi, Hadeel

2017-08-01

Diabetic retinopathy (DR) causes blindness in the working age for people with diabetes in most countries. The increasing number of people with diabetes worldwide suggests that DR will continue to be major contributors to vision loss. Early detection of retinopathy progress in individuals with diabetes is critical for preventing visual loss. Non-proliferative DR (NPDR) is an early stage of DR. Moreover, NPDR can be classified into mild, moderate and severe. This paper proposes a novel morphology-based algorithm for detecting retinal lesions and classifying each case. First, the proposed algorithm detects the three DR lesions, namely haemorrhages, microaneurysms and exudates. Second, we defined and extracted a set of features from detected lesions. The set of selected feature emulates what physicians looked for in classifying NPDR case. Finally, we designed an artificial neural network (ANN) classifier with three layers to classify NPDR to normal, mild, moderate and severe. Bayesian regularisation and resilient backpropagation algorithms are used to train ANN. The accuracy for the proposed classifiers based on Bayesian regularisation and resilient backpropagation algorithms are 96.6 and 89.9, respectively. The obtained results are compared with results of the recent published classifier. Our proposed classifier outperforms the best in terms of sensitivity and specificity.

Deploying a quantum annealing processor to detect tree cover in aerial imagery of California

PubMed Central

Basu, Saikat; Ganguly, Sangram; Michaelis, Andrew; Mukhopadhyay, Supratik; Nemani, Ramakrishna R.

2017-01-01

Quantum annealing is an experimental and potentially breakthrough computational technology for handling hard optimization problems, including problems of computer vision. We present a case study in training a production-scale classifier of tree cover in remote sensing imagery, using early-generation quantum annealing hardware built by D-wave Systems, Inc. Beginning within a known boosting framework, we train decision stumps on texture features and vegetation indices extracted from four-band, one-meter-resolution aerial imagery from the state of California. We then impose a regulated quadratic training objective to select an optimal voting subset from among these stumps. The votes of the subset define the classifier. For optimization, the logical variables in the objective function map to quantum bits in the hardware device, while quadratic couplings encode as the strength of physical interactions between the quantum bits. Hardware design limits the number of couplings between these basic physical entities to five or six. To account for this limitation in mapping large problems to the hardware architecture, we propose a truncation and rescaling of the training objective through a trainable metaparameter. The boosting process on our basic 108- and 508-variable problems, thus constituted, returns classifiers that incorporate a diverse range of color- and texture-based metrics and discriminate tree cover with accuracies as high as 92% in validation and 90% on a test scene encompassing the open space preserves and dense suburban build of Mill Valley, CA. PMID:28241028

Foreign object detection via texture recognition and a neural classifier

NASA Astrophysics Data System (ADS)

Patel, Devesh; Hannah, I.; Davies, E. R.

1993-10-01

It is rate to find pieces of stone, wood, metal, or glass in food packets, but when they occur, these foreign objects (FOs) cause distress to the consumer and concern to the manufacturer. Using x-ray imaging to detect FOs within food bags, hard contaminants such as stone or metal appear darker, whereas soft contaminants such as wood or rubber appear slightly lighter than the food substrate. In this paper we concentrate on the detection of soft contaminants such as small pieces of wood in bags of frozen corn kernels. Convolution masks are used to generate textural features which are then classified into corresponding homogeneous regions on the image using an artificial neural network (ANN) classifier. The separate ANN outputs are combined using a majority operator, and region discrepancies are removed by a median filter. Comparisons with classical classifiers showed the ANN approach to have the best overall combination of characteristics for our particular problem. The detected boundaries are in good agreement with the visually perceived segmentations.

Object recognition based on Google's reverse image search and image similarity

NASA Astrophysics Data System (ADS)

Horváth, András.

2015-12-01

Image classification is one of the most challenging tasks in computer vision and a general multiclass classifier could solve many different tasks in image processing. Classification is usually done by shallow learning for predefined objects, which is a difficult task and very different from human vision, which is based on continuous learning of object classes and one requires years to learn a large taxonomy of objects which are not disjunct nor independent. In this paper I present a system based on Google image similarity algorithm and Google image database, which can classify a large set of different objects in a human like manner, identifying related classes and taxonomies.

Proto-object categorisation and local gist vision using low-level spatial features.

PubMed

Martins, Jaime A; Rodrigues, J M F; du Buf, J M H

2015-09-01

Object categorisation is a research area with significant challenges, especially in conditions with bad lighting, occlusions, different poses and similar objects. This makes systems that rely on precise information unable to perform efficiently, like a robotic arm that needs to know which objects it can reach. We propose a biologically inspired object detection and categorisation framework that relies on robust low-level object shape. Using only edge conspicuity and disparity features for scene figure-ground segregation and object categorisation, a trained neural network classifier can quickly categorise broad object families and consequently bootstrap a low-level scene gist system. We argue that similar processing is possibly located in the parietal pathway leading to the LIP cortex and, via areas V5/MT and MST, providing useful information to the superior colliculus for eye and head control. Copyright © 2015 Elsevier Ireland Ltd. All rights reserved.

Discriminant Analysis of Defective and Non-Defective Field Pea (Pisum sativum L.) into Broad Market Grades Based on Digital Image Features.

PubMed

McDonald, Linda S; Panozzo, Joseph F; Salisbury, Phillip A; Ford, Rebecca

2016-01-01

Field peas (Pisum sativum L.) are generally traded based on seed appearance, which subjectively defines broad market-grades. In this study, we developed an objective Linear Discriminant Analysis (LDA) model to classify market grades of field peas based on seed colour, shape and size traits extracted from digital images. Seeds were imaged in a high-throughput system consisting of a camera and laser positioned over a conveyor belt. Six colour intensity digital images were captured (under 405, 470, 530, 590, 660 and 850nm light) for each seed, and surface height was measured at each pixel by laser. Colour, shape and size traits were compiled across all seed in each sample to determine the median trait values. Defective and non-defective seed samples were used to calibrate and validate the model. Colour components were sufficient to correctly classify all non-defective seed samples into correct market grades. Defective samples required a combination of colour, shape and size traits to achieve 87% and 77% accuracy in market grade classification of calibration and validation sample-sets respectively. Following these results, we used the same colour, shape and size traits to develop an LDA model which correctly classified over 97% of all validation samples as defective or non-defective.

Discriminant Analysis of Defective and Non-Defective Field Pea (Pisum sativum L.) into Broad Market Grades Based on Digital Image Features

PubMed Central

McDonald, Linda S.; Panozzo, Joseph F.; Salisbury, Phillip A.; Ford, Rebecca

2016-01-01

Field peas (Pisum sativum L.) are generally traded based on seed appearance, which subjectively defines broad market-grades. In this study, we developed an objective Linear Discriminant Analysis (LDA) model to classify market grades of field peas based on seed colour, shape and size traits extracted from digital images. Seeds were imaged in a high-throughput system consisting of a camera and laser positioned over a conveyor belt. Six colour intensity digital images were captured (under 405, 470, 530, 590, 660 and 850nm light) for each seed, and surface height was measured at each pixel by laser. Colour, shape and size traits were compiled across all seed in each sample to determine the median trait values. Defective and non-defective seed samples were used to calibrate and validate the model. Colour components were sufficient to correctly classify all non-defective seed samples into correct market grades. Defective samples required a combination of colour, shape and size traits to achieve 87% and 77% accuracy in market grade classification of calibration and validation sample-sets respectively. Following these results, we used the same colour, shape and size traits to develop an LDA model which correctly classified over 97% of all validation samples as defective or non-defective. PMID:27176469

Contextual descriptors and neural networks for scene analysis in VHR SAR images

NASA Astrophysics Data System (ADS)

Del Frate, Fabio; Picchiani, Matteo; Falasco, Alessia; Schiavon, Giovanni

2016-10-01

The development of SAR technology during the last decade has made it possible to collect a huge amount of data over many regions of the world. In particular, the availability of SAR images from different sensors, with metric or sub-metric spatial resolution, offers novel opportunities in different fields as land cover, urban monitoring, soil consumption etc. On the other hand, automatic approaches become crucial for the exploitation of such a huge amount of information. In such a scenario, especially if single polarization images are considered, the main issue is to select appropriate contextual descriptors, since the backscattering coefficient of a single pixel may not be sufficient to classify an object on the scene. In this paper a comparison among three different approaches for contextual features definition is presented so as to design optimum procedures for VHR SAR scene understanding. The first approach is based on Gray Level Co- Occurrence Matrix since it is widely accepted and several studies have used it for land cover classification with SAR data. The second approach is based on the Fourier spectra and it has been already proposed with positive results for this kind of problems, the third one is based on Auto-associative Neural Networks which have been already proven effective for features extraction from polarimetric SAR images. The three methods are evaluated in terms of the accuracy of the classified scene when the features extracted using each method are considered as input to a neural network classificator and applied on different Cosmo-SkyMed spotlight products.

Tracking Electroencephalographic Changes Using Distributions of Linear Models: Application to Propofol-Based Depth of Anesthesia Monitoring.

PubMed

Kuhlmann, Levin; Manton, Jonathan H; Heyse, Bjorn; Vereecke, Hugo E M; Lipping, Tarmo; Struys, Michel M R F; Liley, David T J

2017-04-01

Tracking brain states with electrophysiological measurements often relies on short-term averages of extracted features and this may not adequately capture the variability of brain dynamics. The objective is to assess the hypotheses that this can be overcome by tracking distributions of linear models using anesthesia data, and that anesthetic brain state tracking performance of linear models is comparable to that of a high performing depth of anesthesia monitoring feature. Individuals' brain states are classified by comparing the distribution of linear (auto-regressive moving average-ARMA) model parameters estimated from electroencephalographic (EEG) data obtained with a sliding window to distributions of linear model parameters for each brain state. The method is applied to frontal EEG data from 15 subjects undergoing propofol anesthesia and classified by the observers assessment of alertness/sedation (OAA/S) scale. Classification of the OAA/S score was performed using distributions of either ARMA parameters or the benchmark feature, Higuchi fractal dimension. The highest average testing sensitivity of 59% (chance sensitivity: 17%) was found for ARMA (2,1) models and Higuchi fractal dimension achieved 52%, however, no statistical difference was observed. For the same ARMA case, there was no statistical difference if medians are used instead of distributions (sensitivity: 56%). The model-based distribution approach is not necessarily more effective than a median/short-term average approach, however, it performs well compared with a distribution approach based on a high performing anesthesia monitoring measure. These techniques hold potential for anesthesia monitoring and may be generally applicable for tracking brain states.

Automated analysis of individual sperm cells using stain-free interferometric phase microscopy and machine learning.

PubMed

Mirsky, Simcha K; Barnea, Itay; Levi, Mattan; Greenspan, Hayit; Shaked, Natan T

2017-09-01

Currently, the delicate process of selecting sperm cells to be used for in vitro fertilization (IVF) is still based on the subjective, qualitative analysis of experienced clinicians using non-quantitative optical microscopy techniques. In this work, a method was developed for the automated analysis of sperm cells based on the quantitative phase maps acquired through use of interferometric phase microscopy (IPM). Over 1,400 human sperm cells from 8 donors were imaged using IPM, and an algorithm was designed to digitally isolate sperm cell heads from the quantitative phase maps while taking into consideration both the cell 3D morphology and contents, as well as acquire features describing sperm head morphology. A subset of these features was used to train a support vector machine (SVM) classifier to automatically classify sperm of good and bad morphology. The SVM achieves an area under the receiver operating characteristic curve of 88.59% and an area under the precision-recall curve of 88.67%, as well as precisions of 90% or higher. We believe that our automatic analysis can become the basis for objective and automatic sperm cell selection in IVF. © 2017 International Society for Advancement of Cytometry. © 2017 International Society for Advancement of Cytometry.

The Contribution of the Vaccine Adverse Event Text Mining System to the Classification of Possible Guillain-Barré Syndrome Reports

PubMed Central

Botsis, T.; Woo, E. J.; Ball, R.

2013-01-01

Background We previously demonstrated that a general purpose text mining system, the Vaccine adverse event Text Mining (VaeTM) system, could be used to automatically classify reports of an-aphylaxis for post-marketing safety surveillance of vaccines. Objective To evaluate the ability of VaeTM to classify reports to the Vaccine Adverse Event Reporting System (VAERS) of possible Guillain-Barré Syndrome (GBS). Methods We used VaeTM to extract the key diagnostic features from the text of reports in VAERS. Then, we applied the Brighton Collaboration (BC) case definition for GBS, and an information retrieval strategy (i.e. the vector space model) to quantify the specific information that is included in the key features extracted by VaeTM and compared it with the encoded information that is already stored in VAERS as Medical Dictionary for Regulatory Activities (MedDRA) Preferred Terms (PTs). We also evaluated the contribution of the primary (diagnosis and cause of death) and secondary (second level diagnosis and symptoms) diagnostic VaeTM-based features to the total VaeTM-based information. Results MedDRA captured more information and better supported the classification of reports for GBS than VaeTM (AUC: 0.904 vs. 0.777); the lower performance of VaeTM is likely due to the lack of extraction by VaeTM of specific laboratory results that are included in the BC criteria for GBS. On the other hand, the VaeTM-based classification exhibited greater specificity than the MedDRA-based approach (94.96% vs. 87.65%). Most of the VaeTM-based information was contained in the secondary diagnostic features. Conclusion For GBS, clinical signs and symptoms alone are not sufficient to match MedDRA coding for purposes of case classification, but are preferred if specificity is the priority. PMID:23650490

Kinematic and Pressure Features of Handwriting and Drawing: Preliminary Results Between Patients with Mild Cognitive Impairment, Alzheimer Disease and Healthy Controls

PubMed Central

Garre-Olmo, Josep; Faúndez-Zanuy, Marcos; López-de-Ipiña, Karmele; Calvó-Perxas, Laia; Turró-Garriga, Oriol

2017-01-01

Background: Alzheimer’s disease (AD) is the most common neurodegenerative dementia of old age, and the leading chronic disease contributor to disability and dependence among older people worldwide. Clinically, AD is characterized by a progressive cognitive decline that interferes with the abil-ity to perform the activities of daily living. Handwriting and drawing are complex human activities that entail an intricate blend of cognitive, kinesthetic, and perceptual-motor features. Objective: To compare the kinematic characteristics of handwriting and drawing between patients with AD, patients with mild cognitive impairment (MCI) and healthy controls. Methods: We used a cross-sectional and observational design to assess the kinematic and pressure fea-tures of handwriting and drawing using a computerized system. Participants were asked to copy one sen-tence, write a dictated sentence and an own sentence, copy two and-three dimensions drawings, and to execute the clock drawing test. By means of discriminant analyses, we explored the value of several kin-ematic features in order to classify participants depending on their degree of cognitive functioning. Results: The sample consisted of 52 participants (23 AD, 12 MCI, and 17 healthy controls) with a mean age of 69.7 years (SD=8.11). The degree of correct classification was largely dependent on the nature of the groups to be classified and the specific task, and ranged between 63.5% and 100%. Diagnostic accu-racy based on kinematic measures showed higher specificity values for distinguishing between normal and impaired cognition (MCI and AD), and higher sensitivity was obtained when distinguishing between impaired cognition levels (MCI vs. AD). Conclusion: The kinematic features of writing and drawing procedures, rather than the final product, may be a useful and objective complement to the clinical assessment of patients with cognitive impairment. PMID:28290244

Classification of Hyperspectral Data Based on Guided Filtering and Random Forest

NASA Astrophysics Data System (ADS)

Ma, H.; Feng, W.; Cao, X.; Wang, L.

2017-09-01

Hyperspectral images usually consist of more than one hundred spectral bands, which have potentials to provide rich spatial and spectral information. However, the application of hyperspectral data is still challengeable due to "the curse of dimensionality". In this context, many techniques, which aim to make full use of both the spatial and spectral information, are investigated. In order to preserve the geometrical information, meanwhile, with less spectral bands, we propose a novel method, which combines principal components analysis (PCA), guided image filtering and the random forest classifier (RF). In detail, PCA is firstly employed to reduce the dimension of spectral bands. Secondly, the guided image filtering technique is introduced to smooth land object, meanwhile preserving the edge of objects. Finally, the features are fed into RF classifier. To illustrate the effectiveness of the method, we carry out experiments over the popular Indian Pines data set, which is collected by Airborne Visible/Infrared Imaging Spectrometer (AVIRIS) sensor. By comparing the proposed method with the method of only using PCA or guided image filter, we find that effect of the proposed method is better.

Target discrimination method for SAR images based on semisupervised co-training

NASA Astrophysics Data System (ADS)

Wang, Yan; Du, Lan; Dai, Hui

2018-01-01

Synthetic aperture radar (SAR) target discrimination is usually performed in a supervised manner. However, supervised methods for SAR target discrimination may need lots of labeled training samples, whose acquirement is costly, time consuming, and sometimes impossible. This paper proposes an SAR target discrimination method based on semisupervised co-training, which utilizes a limited number of labeled samples and an abundant number of unlabeled samples. First, Lincoln features, widely used in SAR target discrimination, are extracted from the training samples and partitioned into two sets according to their physical meanings. Second, two support vector machine classifiers are iteratively co-trained with the extracted two feature sets based on the co-training algorithm. Finally, the trained classifiers are exploited to classify the test data. The experimental results on real SAR images data not only validate the effectiveness of the proposed method compared with the traditional supervised methods, but also demonstrate the superiority of co-training over self-training, which only uses one feature set.

Evolving optimised decision rules for intrusion detection using particle swarm paradigm

NASA Astrophysics Data System (ADS)

Sivatha Sindhu, Siva S.; Geetha, S.; Kannan, A.

2012-12-01

The aim of this article is to construct a practical intrusion detection system (IDS) that properly analyses the statistics of network traffic pattern and classify them as normal or anomalous class. The objective of this article is to prove that the choice of effective network traffic features and a proficient machine-learning paradigm enhances the detection accuracy of IDS. In this article, a rule-based approach with a family of six decision tree classifiers, namely Decision Stump, C4.5, Naive Baye's Tree, Random Forest, Random Tree and Representative Tree model to perform the detection of anomalous network pattern is introduced. In particular, the proposed swarm optimisation-based approach selects instances that compose training set and optimised decision tree operate over this trained set producing classification rules with improved coverage, classification capability and generalisation ability. Experiment with the Knowledge Discovery and Data mining (KDD) data set which have information on traffic pattern, during normal and intrusive behaviour shows that the proposed algorithm produces optimised decision rules and outperforms other machine-learning algorithm.

Analyzing Visibility Configurations.

PubMed

Dachsbacher, C

2011-04-01

Many algorithms, such as level of detail rendering and occlusion culling methods, make decisions based on the degree of visibility of an object, but do not analyze the distribution, or structure, of the visible and occluded regions across surfaces. We present an efficient method to classify different visibility configurations and show how this can be used on top of existing methods based on visibility determination. We adapt co-occurrence matrices for visibility analysis and generalize them to operate on clusters of triangular surfaces instead of pixels. We employ machine learning techniques to reliably classify the thus extracted feature vectors. Our method allows perceptually motivated level of detail methods for real-time rendering applications by detecting configurations with expected visual masking. We exemplify the versatility of our method with an analysis of area light visibility configurations in ray tracing and an area-to-area visibility analysis suitable for hierarchical radiosity refinement. Initial results demonstrate the robustness, simplicity, and performance of our method in synthetic scenes, as well as real applications.

An Evaluation of Feature Learning Methods for High Resolution Image Classification

NASA Astrophysics Data System (ADS)

Tokarczyk, P.; Montoya, J.; Schindler, K.

2012-07-01

Automatic image classification is one of the fundamental problems of remote sensing research. The classification problem is even more challenging in high-resolution images of urban areas, where the objects are small and heterogeneous. Two questions arise, namely which features to extract from the raw sensor data to capture the local radiometry and image structure at each pixel or segment, and which classification method to apply to the feature vectors. While classifiers are nowadays well understood, selecting the right features remains a largely empirical process. Here we concentrate on the features. Several methods are evaluated which allow one to learn suitable features from unlabelled image data by analysing the image statistics. In a comparative study, we evaluate unsupervised feature learning with different linear and non-linear learning methods, including principal component analysis (PCA) and deep belief networks (DBN). We also compare these automatically learned features with popular choices of ad-hoc features including raw intensity values, standard combinations like the NDVI, a few PCA channels, and texture filters. The comparison is done in a unified framework using the same images, the target classes, reference data and a Random Forest classifier.

Accelerometer and Camera-Based Strategy for Improved Human Fall Detection.

PubMed

Zerrouki, Nabil; Harrou, Fouzi; Sun, Ying; Houacine, Amrane

2016-12-01

In this paper, we address the problem of detecting human falls using anomaly detection. Detection and classification of falls are based on accelerometric data and variations in human silhouette shape. First, we use the exponentially weighted moving average (EWMA) monitoring scheme to detect a potential fall in the accelerometric data. We used an EWMA to identify features that correspond with a particular type of fall allowing us to classify falls. Only features corresponding with detected falls were used in the classification phase. A benefit of using a subset of the original data to design classification models minimizes training time and simplifies models. Based on features corresponding to detected falls, we used the support vector machine (SVM) algorithm to distinguish between true falls and fall-like events. We apply this strategy to the publicly available fall detection databases from the university of Rzeszow's. Results indicated that our strategy accurately detected and classified fall events, suggesting its potential application to early alert mechanisms in the event of fall situations and its capability for classification of detected falls. Comparison of the classification results using the EWMA-based SVM classifier method with those achieved using three commonly used machine learning classifiers, neural network, K-nearest neighbor and naïve Bayes, proved our model superior.

Inter-relationships between objective handwriting features and executive control among children with developmental dysgraphia

PubMed Central

2018-01-01

Objective To describe handwriting and executive control features and their inter-relationships among children with developmental dysgraphia, in comparison to controls. Method Participants included 64 children, aged 10–12 years, 32 with dysgraphia based on the Handwriting Proficiency Screening Questionnaire (HPSQ) and 32 matched controls. Children copied a paragraph onto paper affixed to a digitizer that supplied handwriting process objective measures (Computerized Penmanship Evaluation Tool (ComPET). Their written product was evaluated by the Hebrew Handwriting Evaluation (HHE). Parents completed the Behavior Rating Inventory of Executive Function (BRIEF) questionnaire about their child's executive control abilities. Results Significant group differences were found for handwriting performance measures (HHE and ComPET) and executive control domains (BRIEF). Based on one discriminate function, including handwriting performance and executive control measures, 98.4% of the participants were correctly classified into groups. Significant correlations were found in each group between working memory and legibility as well as for other executive domains and handwriting measures. Furthermore, twenty percent of the variability of the mean pressure applied towards the writing surface among children with was explained by their 'emotional control' (BRIEF). Conclusion The results strongly suggest consideration of executive control domains to obtain better insight into handwriting impairment characteristics among children with dysgraphia to improve their identification, evaluation and the intervention process. PMID:29689111

Optimal number of features as a function of sample size for various classification rules.

PubMed

Hua, Jianping; Xiong, Zixiang; Lowey, James; Suh, Edward; Dougherty, Edward R

2005-04-15

Given the joint feature-label distribution, increasing the number of features always results in decreased classification error; however, this is not the case when a classifier is designed via a classification rule from sample data. Typically (but not always), for fixed sample size, the error of a designed classifier decreases and then increases as the number of features grows. The potential downside of using too many features is most critical for small samples, which are commonplace for gene-expression-based classifiers for phenotype discrimination. For fixed sample size and feature-label distribution, the issue is to find an optimal number of features. Since only in rare cases is there a known distribution of the error as a function of the number of features and sample size, this study employs simulation for various feature-label distributions and classification rules, and across a wide range of sample and feature-set sizes. To achieve the desired end, finding the optimal number of features as a function of sample size, it employs massively parallel computation. Seven classifiers are treated: 3-nearest-neighbor, Gaussian kernel, linear support vector machine, polynomial support vector machine, perceptron, regular histogram and linear discriminant analysis. Three Gaussian-based models are considered: linear, nonlinear and bimodal. In addition, real patient data from a large breast-cancer study is considered. To mitigate the combinatorial search for finding optimal feature sets, and to model the situation in which subsets of genes are co-regulated and correlation is internal to these subsets, we assume that the covariance matrix of the features is blocked, with each block corresponding to a group of correlated features. Altogether there are a large number of error surfaces for the many cases. These are provided in full on a companion website, which is meant to serve as resource for those working with small-sample classification. For the companion website, please visit http://public.tgen.org/tamu/ofs/ e-dougherty@ee.tamu.edu.

3D Texture Features Mining for MRI Brain Tumor Identification

NASA Astrophysics Data System (ADS)

Rahim, Mohd Shafry Mohd; Saba, Tanzila; Nayer, Fatima; Syed, Afraz Zahra

2014-03-01

Medical image segmentation is a process to extract region of interest and to divide an image into its individual meaningful, homogeneous components. Actually, these components will have a strong relationship with the objects of interest in an image. For computer-aided diagnosis and therapy process, medical image segmentation is an initial mandatory step. Medical image segmentation is a sophisticated and challenging task because of the sophisticated nature of the medical images. Indeed, successful medical image analysis heavily dependent on the segmentation accuracy. Texture is one of the major features to identify region of interests in an image or to classify an object. 2D textures features yields poor classification results. Hence, this paper represents 3D features extraction using texture analysis and SVM as segmentation technique in the testing methodologies.

Actively learning to distinguish suspicious from innocuous anomalies in a batch of vehicle tracks

NASA Astrophysics Data System (ADS)

Qiu, Zhicong; Miller, David J.; Stieber, Brian; Fair, Tim

2014-06-01

We investigate the problem of actively learning to distinguish between two sets of anomalous vehicle tracks, innocuous" and suspicious", starting from scratch, without any initial examples of suspicious" and with no prior knowledge of what an operator would deem suspicious. This two-class problem is challenging because it is a priori unknown which track features may characterize the suspicious class. Furthermore, there is inherent imbalance in the sizes of the labeled innocuous" and suspicious" sets, even after some suspicious examples are identified. We present a comprehensive solution wherein a classifier learns to discriminate suspicious from innocuous based on derived p-value track features. Through active learning, our classifier thus learns the types of anomalies on which to base its discrimination. Our solution encompasses: i) judicious choice of kinematic p-value based features conditioned on the road of origin, along with more explicit features that capture unique vehicle behavior (e.g. U-turns); ii) novel semi-supervised learning that exploits information in the unlabeled (test batch) tracks, and iii) evaluation of several classifier models (logistic regression, SVMs). We find that two active labeling streams are necessary in practice in order to have efficient classifier learning while also forwarding (for labeling) the most actionable tracks. Experiments on wide-area motion imagery (WAMI) tracks, extracted via a system developed by Toyon Research Corporation, demonstrate the strong ROC AUC performance of our system, with sparing use of operator-based active labeling.

On Burst Detection and Prediction in Retweeting Sequence

DTIC Science & Technology

2015-05-22

We conduct a comprehensive empirical analysis of a large microblogging dataset collected from the Sina Weibo and report our observations of burst...whether and how accurate we can predict bursts using classifiers based on the extracted features. Our empirical study of the Sina Weibo data shows the...feasibility of burst prediction using appropriately extracted features and classic classifiers. 1 Introduction Microblogging, such as Twitter and Sina

Adversarial Feature Selection Against Evasion Attacks.

PubMed

Zhang, Fei; Chan, Patrick P K; Biggio, Battista; Yeung, Daniel S; Roli, Fabio

2016-03-01

Pattern recognition and machine learning techniques have been increasingly adopted in adversarial settings such as spam, intrusion, and malware detection, although their security against well-crafted attacks that aim to evade detection by manipulating data at test time has not yet been thoroughly assessed. While previous work has been mainly focused on devising adversary-aware classification algorithms to counter evasion attempts, only few authors have considered the impact of using reduced feature sets on classifier security against the same attacks. An interesting, preliminary result is that classifier security to evasion may be even worsened by the application of feature selection. In this paper, we provide a more detailed investigation of this aspect, shedding some light on the security properties of feature selection against evasion attacks. Inspired by previous work on adversary-aware classifiers, we propose a novel adversary-aware feature selection model that can improve classifier security against evasion attacks, by incorporating specific assumptions on the adversary's data manipulation strategy. We focus on an efficient, wrapper-based implementation of our approach, and experimentally validate its soundness on different application examples, including spam and malware detection.

Evaluation of extreme learning machine for classification of individual and combined finger movements using electromyography on amputees and non-amputees.

PubMed

Anam, Khairul; Al-Jumaily, Adel

2017-01-01

The success of myoelectric pattern recognition (M-PR) mostly relies on the features extracted and classifier employed. This paper proposes and evaluates a fast classifier, extreme learning machine (ELM), to classify individual and combined finger movements on amputees and non-amputees. ELM is a single hidden layer feed-forward network (SLFN) that avoids iterative learning by determining input weights randomly and output weights analytically. Therefore, it can accelerate the training time of SLFNs. In addition to the classifier evaluation, this paper evaluates various feature combinations to improve the performance of M-PR and investigate some feature projections to improve the class separability of the features. Different from other studies on the implementation of ELM in the myoelectric controller, this paper presents a complete and thorough investigation of various types of ELMs including the node-based and kernel-based ELM. Furthermore, this paper provides comparisons of ELMs and other well-known classifiers such as linear discriminant analysis (LDA), k-nearest neighbour (kNN), support vector machine (SVM) and least-square SVM (LS-SVM). The experimental results show the most accurate ELM classifier is radial basis function ELM (RBF-ELM). The comparison of RBF-ELM and other well-known classifiers shows that RBF-ELM is as accurate as SVM and LS-SVM but faster than the SVM family; it is superior to LDA and kNN. The experimental results also indicate that the accuracy gap of the M-PR on the amputees and non-amputees is not too much with the accuracy of 98.55% on amputees and 99.5% on the non-amputees using six electromyography (EMG) channels. Copyright © 2016 Elsevier Ltd. All rights reserved.

Relevance popularity: A term event model based feature selection scheme for text classification.

PubMed

Feng, Guozhong; An, Baiguo; Yang, Fengqin; Wang, Han; Zhang, Libiao

2017-01-01

Feature selection is a practical approach for improving the performance of text classification methods by optimizing the feature subsets input to classifiers. In traditional feature selection methods such as information gain and chi-square, the number of documents that contain a particular term (i.e. the document frequency) is often used. However, the frequency of a given term appearing in each document has not been fully investigated, even though it is a promising feature to produce accurate classifications. In this paper, we propose a new feature selection scheme based on a term event Multinomial naive Bayes probabilistic model. According to the model assumptions, the matching score function, which is based on the prediction probability ratio, can be factorized. Finally, we derive a feature selection measurement for each term after replacing inner parameters by their estimators. On a benchmark English text datasets (20 Newsgroups) and a Chinese text dataset (MPH-20), our numerical experiment results obtained from using two widely used text classifiers (naive Bayes and support vector machine) demonstrate that our method outperformed the representative feature selection methods.

Natural image classification driven by human brain activity

NASA Astrophysics Data System (ADS)

Zhang, Dai; Peng, Hanyang; Wang, Jinqiao; Tang, Ming; Xue, Rong; Zuo, Zhentao

2016-03-01

Natural image classification has been a hot topic in computer vision and pattern recognition research field. Since the performance of an image classification system can be improved by feature selection, many image feature selection methods have been developed. However, the existing supervised feature selection methods are typically driven by the class label information that are identical for different samples from the same class, ignoring with-in class image variability and therefore degrading the feature selection performance. In this study, we propose a novel feature selection method, driven by human brain activity signals collected using fMRI technique when human subjects were viewing natural images of different categories. The fMRI signals associated with subjects viewing different images encode the human perception of natural images, and therefore may capture image variability within- and cross- categories. We then select image features with the guidance of fMRI signals from brain regions with active response to image viewing. Particularly, bag of words features based on GIST descriptor are extracted from natural images for classification, and a sparse regression base feature selection method is adapted to select image features that can best predict fMRI signals. Finally, a classification model is built on the select image features to classify images without fMRI signals. The validation experiments for classifying images from 4 categories of two subjects have demonstrated that our method could achieve much better classification performance than the classifiers built on image feature selected by traditional feature selection methods.

Automated identification of diagnosis and co-morbidity in clinical records.

PubMed

Cano, C; Blanco, A; Peshkin, L

2009-01-01

Automated understanding of clinical records is a challenging task involving various legal and technical difficulties. Clinical free text is inherently redundant, unstructured, and full of acronyms, abbreviations and domain-specific language which make it challenging to mine automatically. There is much effort in the field focused on creating specialized ontology, lexicons and heuristics based on expert knowledge of the domain. However, ad-hoc solutions poorly generalize across diseases or diagnoses. This paper presents a successful approach for a rapid prototyping of a diagnosis classifier based on a popular computational linguistics platform. The corpus consists of several hundred of full length discharge summaries provided by Partners Healthcare. The goal is to identify a diagnosis and assign co-morbidi-ty. Our approach is based on the rapid implementation of a logistic regression classifier using an existing toolkit: LingPipe (http://alias-i.com/lingpipe). We implement and compare three different classifiers. The baseline approach uses character 5-grams as features. The second approach uses a bag-of-words representation enriched with a small additional set of features. The third approach reduces a feature set to the most informative features according to the information content. The proposed systems achieve high performance (average F-micro 0.92) for the task. We discuss the relative merit of the three classifiers. Supplementary material with detailed results is available at: http:// decsai.ugr.es/~ccano/LR/supplementary_ material/ We show that our methodology for rapid prototyping of a domain-unaware system is effective for building an accurate classifier for clinical records.

Three-dimensional object recognitions from two-dimensional images using wavelet transforms and neural networks

NASA Astrophysics Data System (ADS)

Deschenes, Sylvain; Sheng, Yunlong; Chevrette, Paul C.

1998-03-01

3D object classification from 2D IR images is shown. The wavelet transform is used for edge detection. Edge tracking is used for removing noise effectively int he wavelet transform. The invariant Fourier descriptor is used to describe the contour curves. Invariance under out-of-plane rotation is achieved by the feature space trajectory neural network working as a classifier.

Plausibility assessment of a 2-state self-paced mental task-based BCI using the no-control performance analysis.

PubMed

Faradji, Farhad; Ward, Rabab K; Birch, Gary E

2009-06-15

The feasibility of having a self-paced brain-computer interface (BCI) based on mental tasks is investigated. The EEG signals of four subjects performing five mental tasks each are used in the design of a 2-state self-paced BCI. The output of the BCI should only be activated when the subject performs a specific mental task and should remain inactive otherwise. For each subject and each task, the feature coefficient and the classifier that yield the best performance are selected, using the autoregressive coefficients as the features. The classifier with a zero false positive rate and the highest true positive rate is selected as the best classifier. The classifiers tested include: linear discriminant analysis, quadratic discriminant analysis, Mahalanobis discriminant analysis, support vector machine, and radial basis function neural network. The results show that: (1) some classifiers obtained the desired zero false positive rate; (2) the linear discriminant analysis classifier does not yield acceptable performance; (3) the quadratic discriminant analysis classifier outperforms the Mahalanobis discriminant analysis classifier and performs almost as well as the radial basis function neural network; and (4) the support vector machine classifier has the highest true positive rates but unfortunately has nonzero false positive rates in most cases.

GyneScan

PubMed Central

Acharya, U. Rajendra; Sree, S. Vinitha; Kulshreshtha, Sanjeev; Molinari, Filippo; Koh, Joel En Wei; Saba, Luca; Suri, Jasjit S.

2014-01-01

Ovarian cancer is the fifth highest cause of cancer in women and the leading cause of death from gynecological cancers. Accurate diagnosis of ovarian cancer from acquired images is dependent on the expertise and experience of ultrasonographers or physicians, and is therefore, associated with inter observer variabilities. Computer Aided Diagnostic (CAD) techniques use a number of different data mining techniques to automatically predict the presence or absence of cancer, and therefore, are more reliable and accurate. A review of published literature in the field of CAD based ovarian cancer detection indicates that many studies use ultrasound images as the base for analysis. The key objective of this work is to propose an effective adjunct CAD technique called GyneScan for ovarian tumor detection in ultrasound images. In our proposed data mining framework, we extract several texture features based on first order statistics, Gray Level Co-occurrence Matrix and run length matrix. The significant features selected using t-test are then used to train and test several supervised learning based classifiers such as Probabilistic Neural Networks (PNN), Support Vector Machine (SVM), Decision Tree (DT), k-Nearest Neighbor (KNN), and Naïve Bayes (NB). We evaluated the developed framework using 1300 benign and 1300 malignant images. Using 11 significant features in KNN/PNN classifiers, we were able to achieve 100% classification accuracy, sensitivity, specificity, and positive predictive value in detecting ovarian tumor. Even though more validation using larger databases would better establish the robustness of our technique, the preliminary results are promising. This technique could be used as a reliable adjunct method to existing imaging modalities to provide a more confident second opinion on the presence/absence of ovarian tumor. PMID:24325128

Acoustic classification of zooplankton

NASA Astrophysics Data System (ADS)

Martin Traykovski, Linda V.

1998-11-01

Work on the forward problem in zooplankton bioacoustics has resulted in the identification of three categories of acoustic scatterers: elastic-shelled (e.g. pteropods), fluid-like (e.g. euphausiids), and gas-bearing (e.g. siphonophores). The relationship between backscattered energy and animal biomass has been shown to vary by a factor of ~19,000 across these categories, so that to make accurate estimates of zooplankton biomass from acoustic backscatter measurements of the ocean, the acoustic characteristics of the species of interest must be well-understood. This thesis describes the development of both feature based and model based classification techniques to invert broadband acoustic echoes from individual zooplankton for scatterer type, as well as for particular parameters such as animal orientation. The feature based Empirical Orthogonal Function Classifier (EOFC) discriminates scatterer types by identifying characteristic modes of variability in the echo spectra, exploiting only the inherent characteristic structure of the acoustic signatures. The model based Model Parameterisation Classifier (MPC) classifies based on correlation of observed echo spectra with simplified parameterisations of theoretical scattering models for the three classes. The Covariance Mean Variance Classifiers (CMVC) are a set of advanced model based techniques which exploit the full complexity of the theoretical models by searching the entire physical model parameter space without employing simplifying parameterisations. Three different CMVC algorithms were developed: the Integrated Score Classifier (ISC), the Pairwise Score Classifier (PSC) and the Bayesian Probability Classifier (BPC); these classifiers assign observations to a class based on similarities in covariance, mean, and variance, while accounting for model ambiguity and validity. These feature based and model based inversion techniques were successfully applied to several thousand echoes acquired from broadband (~350 kHz-750 kHz) insonifications of live zooplankton collected on Georges Bank and the Gulf of Maine to determine scatterer class. CMVC techniques were also applied to echoes from fluid-like zooplankton (Antarctic krill) to invert for angle of orientation using generic and animal-specific theoretical and empirical models. Application of these inversion techniques in situ will allow correct apportionment of backscattered energy to animal biomass, significantly improving estimates of zooplankton biomass based on acoustic surveys. (Copies available exclusively from MIT Libraries, Rm. 14-0551, Cambridge, MA 02139-4307. Ph. 617-253-5668; Fax 617-253-1690.)

CNN universal machine as classificaton platform: an art-like clustering algorithm.

PubMed

Bálya, David

2003-12-01

Fast and robust classification of feature vectors is a crucial task in a number of real-time systems. A cellular neural/nonlinear network universal machine (CNN-UM) can be very efficient as a feature detector. The next step is to post-process the results for object recognition. This paper shows how a robust classification scheme based on adaptive resonance theory (ART) can be mapped to the CNN-UM. Moreover, this mapping is general enough to include different types of feed-forward neural networks. The designed analogic CNN algorithm is capable of classifying the extracted feature vectors keeping the advantages of the ART networks, such as robust, plastic and fault-tolerant behaviors. An analogic algorithm is presented for unsupervised classification with tunable sensitivity and automatic new class creation. The algorithm is extended for supervised classification. The presented binary feature vector classification is implemented on the existing standard CNN-UM chips for fast classification. The experimental evaluation shows promising performance after 100% accuracy on the training set.

MixDroid: A multi-features and multi-classifiers bagging system for Android malware detection

NASA Astrophysics Data System (ADS)

Huang, Weiqing; Hou, Erhang; Zheng, Liang; Feng, Weimiao

2018-05-01

In the past decade, Android platform has rapidly taken over the mobile market for its superior convenience and open source characteristics. However, with the popularity of Android, malwares targeting on Android devices are increasing rapidly, while the conventional rule-based and expert-experienced approaches are no longer able to handle such explosive growth. In this paper, combining with the theory of natural language processing and machine learning, we not only implement the basic feature extraction of permission application features, but also propose two innovative schemes of feature extraction: Dalvik opcode features and malicious code image, and implement an automatic Android malware detection system MixDroid which is based on multi-features and multi-classifiers. According to our experiment results on 20,000 Android applications, detection accuracy of MixDroid is 98.1%, which proves our schemes' effectiveness in Android malware detection.

Genetic algorithm for the optimization of features and neural networks in ECG signals classification

NASA Astrophysics Data System (ADS)

Li, Hongqiang; Yuan, Danyang; Ma, Xiangdong; Cui, Dianyin; Cao, Lu

2017-01-01

Feature extraction and classification of electrocardiogram (ECG) signals are necessary for the automatic diagnosis of cardiac diseases. In this study, a novel method based on genetic algorithm-back propagation neural network (GA-BPNN) for classifying ECG signals with feature extraction using wavelet packet decomposition (WPD) is proposed. WPD combined with the statistical method is utilized to extract the effective features of ECG signals. The statistical features of the wavelet packet coefficients are calculated as the feature sets. GA is employed to decrease the dimensions of the feature sets and to optimize the weights and biases of the back propagation neural network (BPNN). Thereafter, the optimized BPNN classifier is applied to classify six types of ECG signals. In addition, an experimental platform is constructed for ECG signal acquisition to supply the ECG data for verifying the effectiveness of the proposed method. The GA-BPNN method with the MIT-BIH arrhythmia database achieved a dimension reduction of nearly 50% and produced good classification results with an accuracy of 97.78%. The experimental results based on the established acquisition platform indicated that the GA-BPNN method achieved a high classification accuracy of 99.33% and could be efficiently applied in the automatic identification of cardiac arrhythmias.

Technical support for creating an artificial intelligence system for feature extraction and experimental design

NASA Technical Reports Server (NTRS)

Glick, B. J.

1985-01-01

Techniques for classifying objects into groups or clases go under many different names including, most commonly, cluster analysis. Mathematically, the general problem is to find a best mapping of objects into an index set consisting of class identifiers. When an a priori grouping of objects exists, the process of deriving the classification rules from samples of classified objects is known as discrimination. When such rules are applied to objects of unknown class, the process is denoted classification. The specific problem addressed involves the group classification of a set of objects that are each associated with a series of measurements (ratio, interval, ordinal, or nominal levels of measurement). Each measurement produces one variable in a multidimensional variable space. Cluster analysis techniques are reviewed and methods for incuding geographic location, distance measures, and spatial pattern (distribution) as parameters in clustering are examined. For the case of patterning, measures of spatial autocorrelation are discussed in terms of the kind of data (nominal, ordinal, or interval scaled) to which they may be applied.

Neural network ensemble based CAD system for focal liver lesions from B-mode ultrasound.

PubMed

Virmani, Jitendra; Kumar, Vinod; Kalra, Naveen; Khandelwal, Niranjan

2014-08-01

A neural network ensemble (NNE) based computer-aided diagnostic (CAD) system to assist radiologists in differential diagnosis between focal liver lesions (FLLs), including (1) typical and atypical cases of Cyst, hemangioma (HEM) and metastatic carcinoma (MET) lesions, (2) small and large hepatocellular carcinoma (HCC) lesions, along with (3) normal (NOR) liver tissue is proposed in the present work. Expert radiologists, visualize the textural characteristics of regions inside and outside the lesions to differentiate between different FLLs, accordingly texture features computed from inside lesion regions of interest (IROIs) and texture ratio features computed from IROIs and surrounding lesion regions of interests (SROIs) are taken as input. Principal component analysis (PCA) is used for reducing the dimensionality of the feature space before classifier design. The first step of classification module consists of a five class PCA-NN based primary classifier which yields probability outputs for five liver image classes. The second step of classification module consists of ten binary PCA-NN based secondary classifiers for NOR/Cyst, NOR/HEM, NOR/HCC, NOR/MET, Cyst/HEM, Cyst/HCC, Cyst/MET, HEM/HCC, HEM/MET and HCC/MET classes. The probability outputs of five class PCA-NN based primary classifier is used to determine the first two most probable classes for a test instance, based on which it is directed to the corresponding binary PCA-NN based secondary classifier for crisp classification between two classes. By including the second step of the classification module, classification accuracy increases from 88.7 % to 95 %. The promising results obtained by the proposed system indicate its usefulness to assist radiologists in differential diagnosis of FLLs.

Design of an Adaptive Human-Machine System Based on Dynamical Pattern Recognition of Cognitive Task-Load.

PubMed

Zhang, Jianhua; Yin, Zhong; Wang, Rubin

2017-01-01

This paper developed a cognitive task-load (CTL) classification algorithm and allocation strategy to sustain the optimal operator CTL levels over time in safety-critical human-machine integrated systems. An adaptive human-machine system is designed based on a non-linear dynamic CTL classifier, which maps a set of electroencephalogram (EEG) and electrocardiogram (ECG) related features to a few CTL classes. The least-squares support vector machine (LSSVM) is used as dynamic pattern classifier. A series of electrophysiological and performance data acquisition experiments were performed on seven volunteer participants under a simulated process control task environment. The participant-specific dynamic LSSVM model is constructed to classify the instantaneous CTL into five classes at each time instant. The initial feature set, comprising 56 EEG and ECG related features, is reduced to a set of 12 salient features (including 11 EEG-related features) by using the locality preserving projection (LPP) technique. An overall correct classification rate of about 80% is achieved for the 5-class CTL classification problem. Then the predicted CTL is used to adaptively allocate the number of process control tasks between operator and computer-based controller. Simulation results showed that the overall performance of the human-machine system can be improved by using the adaptive automation strategy proposed.

Classifying Higher Education Institutions in Korea: A Performance-Based Approach

ERIC Educational Resources Information Center

Shin, Jung Cheol

2009-01-01

The purpose of this study was to classify higher education institutions according to institutional performance rather than predetermined benchmarks. Institutional performance was defined as research performance and classified using Hierarchical Cluster Analysis, a statistical method that classifies objects according to specified classification…

Text Classification for Assisting Moderators in Online Health Communities

PubMed Central

Huh, Jina; Yetisgen-Yildiz, Meliha; Pratt, Wanda

2013-01-01

Objectives Patients increasingly visit online health communities to get help on managing health. The large scale of these online communities makes it impossible for the moderators to engage in all conversations; yet, some conversations need their expertise. Our work explores low-cost text classification methods to this new domain of determining whether a thread in an online health forum needs moderators’ help. Methods We employed a binary classifier on WebMD’s online diabetes community data. To train the classifier, we considered three feature types: (1) word unigram, (2) sentiment analysis features, and (3) thread length. We applied feature selection methods based on χ2 statistics and under sampling to account for unbalanced data. We then performed a qualitative error analysis to investigate the appropriateness of the gold standard. Results Using sentiment analysis features, feature selection methods, and balanced training data increased the AUC value up to 0.75 and the F1-score up to 0.54 compared to the baseline of using word unigrams with no feature selection methods on unbalanced data (0.65 AUC and 0.40 F1-score). The error analysis uncovered additional reasons for why moderators respond to patients’ posts. Discussion We showed how feature selection methods and balanced training data can improve the overall classification performance. We present implications of weighing precision versus recall for assisting moderators of online health communities. Our error analysis uncovered social, legal, and ethical issues around addressing community members’ needs. We also note challenges in producing a gold standard, and discuss potential solutions for addressing these challenges. Conclusion Social media environments provide popular venues in which patients gain health-related information. Our work contributes to understanding scalable solutions for providing moderators’ expertise in these large-scale, social media environments. PMID:24025513

Fuzzy Kernel k-Medoids algorithm for anomaly detection problems

NASA Astrophysics Data System (ADS)

Rustam, Z.; Talita, A. S.

2017-07-01

Intrusion Detection System (IDS) is an essential part of security systems to strengthen the security of information systems. IDS can be used to detect the abuse by intruders who try to get into the network system in order to access and utilize the available data sources in the system. There are two approaches of IDS, Misuse Detection and Anomaly Detection (behavior-based intrusion detection). Fuzzy clustering-based methods have been widely used to solve Anomaly Detection problems. Other than using fuzzy membership concept to determine the object to a cluster, other approaches as in combining fuzzy and possibilistic membership or feature-weighted based methods are also used. We propose Fuzzy Kernel k-Medoids that combining fuzzy and possibilistic membership as a powerful method to solve anomaly detection problem since on numerical experiment it is able to classify IDS benchmark data into five different classes simultaneously. We classify IDS benchmark data KDDCup'99 data set into five different classes simultaneously with the best performance was achieved by using 30 % of training data with clustering accuracy reached 90.28 percent.

VizieR Online Data Catalog: SDSS-DR8 galaxies classified by WND-CHARM (Kuminski+, 2016)

NASA Astrophysics Data System (ADS)

Kuminski, E.; Shamir, L.

2016-06-01

The image analysis method used to classify the images is WND-CHARM (wndchrm; Shamir et al. 2008, BMC Source Code for Biology and Medicine, 3: 13; 2010PLSCB...6E0974S; 2013ascl.soft12002S), which first computes 2885 numerical descriptors from each SDSS image such as textures, edges, shapes), the statistical distribution of the pixel intensities, the polynomial decomposition of the image, and fractal features. These features are extracted from the raw pixels, as well as the image transforms and multi-order image transforms. See section 2 for further explanations. In a similar way than the catalog we also compiled a catalog of all objects with spectra in DR8. For each object, that catalog contains the spec ObjID, the R.A., the decl., the z, z error, the certainty of classification as elliptical, the certainty of classification as spiral, and the certainty of classification as a star. See section 3.1 for further explanations. (2 data files).

Improved characterization of molecular phenotypes in breast lesions using 18F-FDG PET image homogeneity

NASA Astrophysics Data System (ADS)

Cao, Kunlin; Bhagalia, Roshni; Sood, Anup; Brogi, Edi; Mellinghoff, Ingo K.; Larson, Steven M.

2015-03-01

Positron emission tomography (PET) using uorodeoxyglucose (18F-FDG) is commonly used in the assessment of breast lesions by computing voxel-wise standardized uptake value (SUV) maps. Simple metrics derived from ensemble properties of SUVs within each identified breast lesion are routinely used for disease diagnosis. The maximum SUV within the lesion (SUVmax) is the most popular of these metrics. However these simple metrics are known to be error-prone and are susceptible to image noise. Finding reliable SUV map-based features that correlate to established molecular phenotypes of breast cancer (viz. estrogen receptor (ER), progesterone receptor (PR) and human epidermal growth factor receptor 2 (HER2) expression) will enable non-invasive disease management. This study investigated 36 SUV features based on first and second order statistics, local histograms and texture of segmented lesions to predict ER and PR expression in 51 breast cancer patients. True ER and PR expression was obtained via immunohistochemistry (IHC) of tissue samples from each lesion. A supervised learning, adaptive boosting-support vector machine (AdaBoost-SVM), framework was used to select a subset of features to classify breast lesions into distinct phenotypes. Performance of the trained multi-feature classifier was compared against the baseline single-feature SUVmax classifier using receiver operating characteristic (ROC) curves. Results show that texture features encoding local lesion homogeneity extracted from gray-level co-occurrence matrices are the strongest discriminator of lesion ER expression. In particular, classifiers including these features increased prediction accuracy from 0.75 (baseline) to 0.82 and the area under the ROC curve from 0.64 (baseline) to 0.75.

Mineralogy and Temperature-induced Spectral Investigations of A-type Asteroids 246 Asporina and 446 Aeternitas

NASA Technical Reports Server (NTRS)

Reddy, V.; Hardersen, P. S.; Gaffey, M. J.; Abell, P. A.

2005-01-01

A-type asteroids are a relatively rare taxonomic class with no more than 17 known objects. They were first identified as a separate group of R-type asteroids based on broadband spectrophotometry by, and were later classified based on ECAS data by Tholen (1984). These asteroids have moderately high albedos (0.13-0.39), extremely reddish slopes shortward of 0.7 m and a strong absorption feature centered at approx. 1.05 m. More recent surveys like the Small Main-Belt Asteroid Spectroscopic Survey (SMASS) and SMASS II have expanded the taxonomic classes including the A-type, adding 12 new asteroids to the original five.

Object-based benefits without object-based representations.

PubMed

Fougnie, Daryl; Cormiea, Sarah M; Alvarez, George A

2013-08-01

Influential theories of visual working memory have proposed that the basic units of memory are integrated object representations. Key support for this proposal is provided by the same object benefit: It is easier to remember multiple features of a single object than the same set of features distributed across multiple objects. Here, we replicate the object benefit but demonstrate that features are not stored as single, integrated representations. Specifically, participants could remember 10 features better when arranged in 5 objects compared to 10 objects, yet memory for one object feature was largely independent of memory for the other object feature. These results rule out the possibility that integrated representations drive the object benefit and require a revision of the concept of object-based memory representations. We propose that working memory is object-based in regard to the factors that enhance performance but feature based in regard to the level of representational failure. PsycINFO Database Record (c) 2013 APA, all rights reserved.

Dimensionality Reduction Through Classifier Ensembles

NASA Technical Reports Server (NTRS)

Oza, Nikunj C.; Tumer, Kagan; Norwig, Peter (Technical Monitor)

1999-01-01

In data mining, one often needs to analyze datasets with a very large number of attributes. Performing machine learning directly on such data sets is often impractical because of extensive run times, excessive complexity of the fitted model (often leading to overfitting), and the well-known "curse of dimensionality." In practice, to avoid such problems, feature selection and/or extraction are often used to reduce data dimensionality prior to the learning step. However, existing feature selection/extraction algorithms either evaluate features by their effectiveness across the entire data set or simply disregard class information altogether (e.g., principal component analysis). Furthermore, feature extraction algorithms such as principal components analysis create new features that are often meaningless to human users. In this article, we present input decimation, a method that provides "feature subsets" that are selected for their ability to discriminate among the classes. These features are subsequently used in ensembles of classifiers, yielding results superior to single classifiers, ensembles that use the full set of features, and ensembles based on principal component analysis on both real and synthetic datasets.

Pattern Recognition Approaches for Breast Cancer DCE-MRI Classification: A Systematic Review.

PubMed

Fusco, Roberta; Sansone, Mario; Filice, Salvatore; Carone, Guglielmo; Amato, Daniela Maria; Sansone, Carlo; Petrillo, Antonella

2016-01-01

We performed a systematic review of several pattern analysis approaches for classifying breast lesions using dynamic, morphological, and textural features in dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI). Several machine learning approaches, namely artificial neural networks (ANN), support vector machines (SVM), linear discriminant analysis (LDA), tree-based classifiers (TC), and Bayesian classifiers (BC), and features used for classification are described. The findings of a systematic review of 26 studies are presented. The sensitivity and specificity are respectively 91 and 83 % for ANN, 85 and 82 % for SVM, 96 and 85 % for LDA, 92 and 87 % for TC, and 82 and 85 % for BC. The sensitivity and specificity are respectively 82 and 74 % for dynamic features, 93 and 60 % for morphological features, 88 and 81 % for textural features, 95 and 86 % for a combination of dynamic and morphological features, and 88 and 84 % for a combination of dynamic, morphological, and other features. LDA and TC have the best performance. A combination of dynamic and morphological features gives the best performance.

Sensor feature fusion for detecting buried objects

DOE Office of Scientific and Technical Information (OSTI.GOV)

Clark, G.A.; Sengupta, S.K.; Sherwood, R.J.

1993-04-01

Given multiple registered images of the earth`s surface from dual-band sensors, our system fuses information from the sensors to reduce the effects of clutter and improve the ability to detect buried or surface target sites. The sensor suite currently includes two sensors (5 micron and 10 micron wavelengths) and one ground penetrating radar (GPR) of the wide-band pulsed synthetic aperture type. We use a supervised teaming pattern recognition approach to detect metal and plastic land mines buried in soil. The overall process consists of four main parts: Preprocessing, feature extraction, feature selection, and classification. These parts are used in amore » two step process to classify a subimage. Thee first step, referred to as feature selection, determines the features of sub-images which result in the greatest separability among the classes. The second step, image labeling, uses the selected features and the decisions from a pattern classifier to label the regions in the image which are likely to correspond to buried mines. We extract features from the images, and use feature selection algorithms to select only the most important features according to their contribution to correct detections. This allows us to save computational complexity and determine which of the sensors add value to the detection system. The most important features from the various sensors are fused using supervised teaming pattern classifiers (including neural networks). We present results of experiments to detect buried land mines from real data, and evaluate the usefulness of fusing feature information from multiple sensor types, including dual-band infrared and ground penetrating radar. The novelty of the work lies mostly in the combination of the algorithms and their application to the very important and currently unsolved operational problem of detecting buried land mines from an airborne standoff platform.« less

Event Recognition Based on Deep Learning in Chinese Texts

PubMed Central

Zhang, Yajun; Liu, Zongtian; Zhou, Wen

2016-01-01

Event recognition is the most fundamental and critical task in event-based natural language processing systems. Existing event recognition methods based on rules and shallow neural networks have certain limitations. For example, extracting features using methods based on rules is difficult; methods based on shallow neural networks converge too quickly to a local minimum, resulting in low recognition precision. To address these problems, we propose the Chinese emergency event recognition model based on deep learning (CEERM). Firstly, we use a word segmentation system to segment sentences. According to event elements labeled in the CEC 2.0 corpus, we classify words into five categories: trigger words, participants, objects, time and location. Each word is vectorized according to the following six feature layers: part of speech, dependency grammar, length, location, distance between trigger word and core word and trigger word frequency. We obtain deep semantic features of words by training a feature vector set using a deep belief network (DBN), then analyze those features in order to identify trigger words by means of a back propagation neural network. Extensive testing shows that the CEERM achieves excellent recognition performance, with a maximum F-measure value of 85.17%. Moreover, we propose the dynamic-supervised DBN, which adds supervised fine-tuning to a restricted Boltzmann machine layer by monitoring its training performance. Test analysis reveals that the new DBN improves recognition performance and effectively controls the training time. Although the F-measure increases to 88.11%, the training time increases by only 25.35%. PMID:27501231

Event Recognition Based on Deep Learning in Chinese Texts.

PubMed

Zhang, Yajun; Liu, Zongtian; Zhou, Wen

2016-01-01

Event recognition is the most fundamental and critical task in event-based natural language processing systems. Existing event recognition methods based on rules and shallow neural networks have certain limitations. For example, extracting features using methods based on rules is difficult; methods based on shallow neural networks converge too quickly to a local minimum, resulting in low recognition precision. To address these problems, we propose the Chinese emergency event recognition model based on deep learning (CEERM). Firstly, we use a word segmentation system to segment sentences. According to event elements labeled in the CEC 2.0 corpus, we classify words into five categories: trigger words, participants, objects, time and location. Each word is vectorized according to the following six feature layers: part of speech, dependency grammar, length, location, distance between trigger word and core word and trigger word frequency. We obtain deep semantic features of words by training a feature vector set using a deep belief network (DBN), then analyze those features in order to identify trigger words by means of a back propagation neural network. Extensive testing shows that the CEERM achieves excellent recognition performance, with a maximum F-measure value of 85.17%. Moreover, we propose the dynamic-supervised DBN, which adds supervised fine-tuning to a restricted Boltzmann machine layer by monitoring its training performance. Test analysis reveals that the new DBN improves recognition performance and effectively controls the training time. Although the F-measure increases to 88.11%, the training time increases by only 25.35%.

Understanding user intents in online health forums.

PubMed

Zhang, Thomas; Cho, Jason H D; Zhai, Chengxiang

2015-07-01

Online health forums provide a convenient way for patients to obtain medical information and connect with physicians and peers outside of clinical settings. However, large quantities of unstructured and diversified content generated on these forums make it difficult for users to digest and extract useful information. Understanding user intents would enable forums to find and recommend relevant information to users by filtering out threads that do not match particular intents. In this paper, we derive a taxonomy of intents to capture user information needs in online health forums and propose novel pattern-based features for use with a multiclass support vector machine (SVM) classifier to classify original thread posts according to their underlying intents. Since no dataset existed for this task, we employ three annotators to manually label a dataset of 1192 HealthBoards posts spanning four forum topics. Experimental results show that a SVM using pattern-based features is highly capable of identifying user intents in forum posts, reaching a maximum precision of 75%, and that a SVM-based hierarchical classifier using both pattern and word features outperforms its SVM counterpart that uses only word features. Furthermore, comparable classification performance can be achieved by training and testing on posts from different forum topics.

Hailstone classifier based on Rough Set Theory

NASA Astrophysics Data System (ADS)

Wan, Huisong; Jiang, Shuming; Wei, Zhiqiang; Li, Jian; Li, Fengjiao

2017-09-01

The Rough Set Theory was used for the construction of the hailstone classifier. Firstly, the database of the radar image feature was constructed. It included transforming the base data reflected by the Doppler radar into the bitmap format which can be seen. Then through the image processing, the color, texture, shape and other dimensional features should be extracted and saved as the characteristic database to provide data support for the follow-up work. Secondly, Through the Rough Set Theory, a machine for hailstone classifications can be built to achieve the hailstone samples’ auto-classification.

Active acoustic classification via transient resonance scattering

NASA Astrophysics Data System (ADS)

Gaunaurd, Guillermo C.

1992-12-01

The echoes reflected by a sound ping emerging from active sonar when it interacts with a target in its path can be remotely sensed by a receiver. The presented approach capitalizes on an air inverse scattering method that exploits the presence of certain resonance features in these echoes returned by targets to classify them. Classifying underwater objects is important to naval programs such as mine countermeasures (MC) and anti-submarine warfare (ASW) to preclude wasting of ordnance on false targets. Although the classification of complex shapes is still a formidable task, considerable progress has been made in classifying simple shapes such as spheroidal or cylindrical shells. The briefly overviewed methodology has emphasized the extraction, isolation, and labeling of resonance features hidden within the echo, but little has been said about how these could be used to classify a target. A couple of simple examples illustrate exactly how these resonances can be linked to the physical characteristics of the target, allowing for its unambiguous characterization. The procedure, although illustrated with active acoustics (i.e., sonar), can be extended to any active return from any sensor, including radar.

Comparing ensemble learning methods based on decision tree classifiers for protein fold recognition.

PubMed

Bardsiri, Mahshid Khatibi; Eftekhari, Mahdi

2014-01-01

In this paper, some methods for ensemble learning of protein fold recognition based on a decision tree (DT) are compared and contrasted against each other over three datasets taken from the literature. According to previously reported studies, the features of the datasets are divided into some groups. Then, for each of these groups, three ensemble classifiers, namely, random forest, rotation forest and AdaBoost.M1 are employed. Also, some fusion methods are introduced for combining the ensemble classifiers obtained in the previous step. After this step, three classifiers are produced based on the combination of classifiers of types random forest, rotation forest and AdaBoost.M1. Finally, the three different classifiers achieved are combined to make an overall classifier. Experimental results show that the overall classifier obtained by the genetic algorithm (GA) weighting fusion method, is the best one in comparison to previously applied methods in terms of classification accuracy.

Breast Cancer Recognition Using a Novel Hybrid Intelligent Method

PubMed Central

Addeh, Jalil; Ebrahimzadeh, Ata

2012-01-01

Breast cancer is the second largest cause of cancer deaths among women. At the same time, it is also among the most curable cancer types if it can be diagnosed early. This paper presents a novel hybrid intelligent method for recognition of breast cancer tumors. The proposed method includes three main modules: the feature extraction module, the classifier module, and the optimization module. In the feature extraction module, fuzzy features are proposed as the efficient characteristic of the patterns. In the classifier module, because of the promising generalization capability of support vector machines (SVM), a SVM-based classifier is proposed. In support vector machine training, the hyperparameters have very important roles for its recognition accuracy. Therefore, in the optimization module, the bees algorithm (BA) is proposed for selecting appropriate parameters of the classifier. The proposed system is tested on Wisconsin Breast Cancer database and simulation results show that the recommended system has a high accuracy. PMID:23626945

The value of nodal information in predicting lung cancer relapse using 4DPET/4DCT

DOE Office of Scientific and Technical Information (OSTI.GOV)

Li, Heyse, E-mail: heyse.li@mail.utoronto.ca; Becker, Nathan; Raman, Srinivas

2015-08-15

Purpose: There is evidence that computed tomography (CT) and positron emission tomography (PET) imaging metrics are prognostic and predictive in nonsmall cell lung cancer (NSCLC) treatment outcomes. However, few studies have explored the use of standardized uptake value (SUV)-based image features of nodal regions as predictive features. The authors investigated and compared the use of tumor and node image features extracted from the radiotherapy target volumes to predict relapse in a cohort of NSCLC patients undergoing chemoradiation treatment. Methods: A prospective cohort of 25 patients with locally advanced NSCLC underwent 4DPET/4DCT imaging for radiation planning. Thirty-seven image features were derivedmore » from the CT-defined volumes and SUVs of the PET image from both the tumor and nodal target regions. The machine learning methods of logistic regression and repeated stratified five-fold cross-validation (CV) were used to predict local and overall relapses in 2 yr. The authors used well-known feature selection methods (Spearman’s rank correlation, recursive feature elimination) within each fold of CV. Classifiers were ranked on their Matthew’s correlation coefficient (MCC) after CV. Area under the curve, sensitivity, and specificity values are also presented. Results: For predicting local relapse, the best classifier found had a mean MCC of 0.07 and was composed of eight tumor features. For predicting overall relapse, the best classifier found had a mean MCC of 0.29 and was composed of a single feature: the volume greater than 0.5 times the maximum SUV (N). Conclusions: The best classifier for predicting local relapse had only tumor features. In contrast, the best classifier for predicting overall relapse included a node feature. Overall, the methods showed that nodes add value in predicting overall relapse but not local relapse.« less

Method of generating features optimal to a dataset and classifier

DOE Office of Scientific and Technical Information (OSTI.GOV)

Bruillard, Paul J.; Gosink, Luke J.; Jarman, Kenneth D.

A method of generating features optimal to a particular dataset and classifier is disclosed. A dataset of messages is inputted and a classifier is selected. An algebra of features is encoded. Computable features that are capable of describing the dataset from the algebra of features are selected. Irredundant features that are optimal for the classifier and the dataset are selected.

Examining change detection approaches for tropical mangrove monitoring

USGS Publications Warehouse

Myint, Soe W.; Franklin, Janet; Buenemann, Michaela; Kim, Won; Giri, Chandra

2014-01-01

This study evaluated the effectiveness of different band combinations and classifiers (unsupervised, supervised, object-oriented nearest neighbor, and object-oriented decision rule) for quantifying mangrove forest change using multitemporal Landsat data. A discriminant analysis using spectra of different vegetation types determined that bands 2 (0.52 to 0.6 μm), 5 (1.55 to 1.75 μm), and 7 (2.08 to 2.35 μm) were the most effective bands for differentiating mangrove forests from surrounding land cover types. A ranking of thirty-six change maps, produced by comparing the classification accuracy of twelve change detection approaches, was used. The object-based Nearest Neighbor classifier produced the highest mean overall accuracy (84 percent) regardless of band combinations. The automated decision rule-based approach (mean overall accuracy of 88 percent) as well as a composite of bands 2, 5, and 7 used with the unsupervised classifier and the same composite or all band difference with the object-oriented Nearest Neighbor classifier were the most effective approaches.

Two-view information fusion for improvement of computer-aided detection (CAD) of breast masses on mammograms

NASA Astrophysics Data System (ADS)

Wei, Jun; Sahiner, Berkman; Hadjiiski, Lubomir M.; Chan, Heang-Ping; Helvie, Mark A.; Roubidoux, Marilyn A.; Zhou, Chuan; Ge, Jun; Zhang, Yiheng

2006-03-01

We are developing a two-view information fusion method to improve the performance of our CAD system for mass detection. Mass candidates on each mammogram were first detected with our single-view CAD system. Potential object pairs on the two-view mammograms were then identified by using the distance between the object and the nipple. Morphological features, Hessian feature, correlation coefficients between the two paired objects and texture features were used as input to train a similarity classifier that estimated a similarity scores for each pair. Finally, a linear discriminant analysis (LDA) classifier was used to fuse the score from the single-view CAD system and the similarity score. A data set of 475 patients containing 972 mammograms with 475 biopsy-proven masses was used to train and test the CAD system. All cases contained the CC view and the MLO or LM view. We randomly divided the data set into two independent sets of 243 cases and 232 cases. The training and testing were performed using the 2-fold cross validation method. The detection performance of the CAD system was assessed by free response receiver operating characteristic (FROC) analysis. The average test FROC curve was obtained from averaging the FP rates at the same sensitivity along the two corresponding test FROC curves from the 2-fold cross validation. At the case-based sensitivities of 90%, 85% and 80% on the test set, the single-view CAD system achieved an FP rate of 2.0, 1.5, and 1.2 FPs/image, respectively. With the two-view fusion system, the FP rates were reduced to 1.7, 1.3, and 1.0 FPs/image, respectively, at the corresponding sensitivities. The improvement was found to be statistically significant (p<0.05) by the AFROC method. Our results indicate that the two-view fusion scheme can improve the performance of mass detection on mammograms.

Off-lexicon online Arabic handwriting recognition using neural network

NASA Astrophysics Data System (ADS)

Yahia, Hamdi; Chaabouni, Aymen; Boubaker, Houcine; Alimi, Adel M.

2017-03-01

This paper highlights a new method for online Arabic handwriting recognition based on graphemes segmentation. The main contribution of our work is to explore the utility of Beta-elliptic model in segmentation and features extraction for online handwriting recognition. Indeed, our method consists in decomposing the input signal into continuous part called graphemes based on Beta-Elliptical model, and classify them according to their position in the pseudo-word. The segmented graphemes are then described by the combination of geometric features and trajectory shape modeling. The efficiency of the considered features has been evaluated using feed forward neural network classifier. Experimental results using the benchmarking ADAB Database show the performance of the proposed method.

A Sieving ANN for Emotion-Based Movie Clip Classification

NASA Astrophysics Data System (ADS)

Watanapa, Saowaluk C.; Thipakorn, Bundit; Charoenkitkarn, Nipon

Effective classification and analysis of semantic contents are very important for the content-based indexing and retrieval of video database. Our research attempts to classify movie clips into three groups of commonly elicited emotions, namely excitement, joy and sadness, based on a set of abstract-level semantic features extracted from the film sequence. In particular, these features consist of six visual and audio measures grounded on the artistic film theories. A unique sieving-structured neural network is proposed to be the classifying model due to its robustness. The performance of the proposed model is tested with 101 movie clips excerpted from 24 award-winning and well-known Hollywood feature films. The experimental result of 97.8% correct classification rate, measured against the collected human-judges, indicates the great potential of using abstract-level semantic features as an engineered tool for the application of video-content retrieval/indexing.

A new strategy for snow-cover mapping using remote sensing data and ensemble based systems techniques

NASA Astrophysics Data System (ADS)

Roberge, S.; Chokmani, K.; De Sève, D.

2012-04-01

The snow cover plays an important role in the hydrological cycle of Quebec (Eastern Canada). Consequently, evaluating its spatial extent interests the authorities responsible for the management of water resources, especially hydropower companies. The main objective of this study is the development of a snow-cover mapping strategy using remote sensing data and ensemble based systems techniques. Planned to be tested in a near real-time operational mode, this snow-cover mapping strategy has the advantage to provide the probability of a pixel to be snow covered and its uncertainty. Ensemble systems are made of two key components. First, a method is needed to build an ensemble of classifiers that is diverse as much as possible. Second, an approach is required to combine the outputs of individual classifiers that make up the ensemble in such a way that correct decisions are amplified, and incorrect ones are cancelled out. In this study, we demonstrate the potential of ensemble systems to snow-cover mapping using remote sensing data. The chosen classifier is a sequential thresholds algorithm using NOAA-AVHRR data adapted to conditions over Eastern Canada. Its special feature is the use of a combination of six sequential thresholds varying according to the day in the winter season. Two versions of the snow-cover mapping algorithm have been developed: one is specific for autumn (from October 1st to December 31st) and the other for spring (from March 16th to May 31st). In order to build the ensemble based system, different versions of the algorithm are created by varying randomly its parameters. One hundred of the versions are included in the ensemble. The probability of a pixel to be snow, no-snow or cloud covered corresponds to the amount of votes the pixel has been classified as such by all classifiers. The overall performance of ensemble based mapping is compared to the overall performance of the chosen classifier, and also with ground observations at meteorological stations.

Image fusion using sparse overcomplete feature dictionaries

DOEpatents

Brumby, Steven P.; Bettencourt, Luis; Kenyon, Garrett T.; Chartrand, Rick; Wohlberg, Brendt

2015-10-06

Approaches for deciding what individuals in a population of visual system "neurons" are looking for using sparse overcomplete feature dictionaries are provided. A sparse overcomplete feature dictionary may be learned for an image dataset and a local sparse representation of the image dataset may be built using the learned feature dictionary. A local maximum pooling operation may be applied on the local sparse representation to produce a translation-tolerant representation of the image dataset. An object may then be classified and/or clustered within the translation-tolerant representation of the image dataset using a supervised classification algorithm and/or an unsupervised clustering algorithm.

Probabilistic Multi-Person Tracking Using Dynamic Bayes Networks

NASA Astrophysics Data System (ADS)

Klinger, T.; Rottensteiner, F.; Heipke, C.

2015-08-01

Tracking-by-detection is a widely used practice in recent tracking systems. These usually rely on independent single frame detections that are handled as observations in a recursive estimation framework. If these observations are imprecise the generated trajectory is prone to be updated towards a wrong position. In contrary to existing methods our novel approach uses a Dynamic Bayes Network in which the state vector of a recursive Bayes filter, as well as the location of the tracked object in the image are modelled as unknowns. These unknowns are estimated in a probabilistic framework taking into account a dynamic model, and a state-of-the-art pedestrian detector and classifier. The classifier is based on the Random Forest-algorithm and is capable of being trained incrementally so that new training samples can be incorporated at runtime. This allows the classifier to adapt to the changing appearance of a target and to unlearn outdated features. The approach is evaluated on a publicly available benchmark. The results confirm that our approach is well suited for tracking pedestrians over long distances while at the same time achieving comparatively good geometric accuracy.

Salient object detection method based on multiple semantic features

NASA Astrophysics Data System (ADS)

Wang, Chunyang; Yu, Chunyan; Song, Meiping; Wang, Yulei

2018-04-01

The existing salient object detection model can only detect the approximate location of salient object, or highlight the background, to resolve the above problem, a salient object detection method was proposed based on image semantic features. First of all, three novel salient features were presented in this paper, including object edge density feature (EF), object semantic feature based on the convex hull (CF) and object lightness contrast feature (LF). Secondly, the multiple salient features were trained with random detection windows. Thirdly, Naive Bayesian model was used for combine these features for salient detection. The results on public datasets showed that our method performed well, the location of salient object can be fixed and the salient object can be accurately detected and marked by the specific window.

Object Detection using the Kinect

DTIC Science & Technology

2012-03-01

Kinect camera and point cloud data from the Kinect’s structured light stereo system (figure 1). We obtain reasonable results using a single prototype...same manner we present in this report. For example, at Willow Garage , Steder uses a 3-D feature he developed to classify objects directly from point...detecting backpacks using the data available from the Kinect sensor. 4 3.1 Point Cloud Filtering Dense point clouds derived from stereo are notoriously

Use of border information in the classification of mammographic masses

NASA Astrophysics Data System (ADS)

Varela, C.; Timp, S.; Karssemeijer, N.

2006-01-01

We are developing a new method to characterize the margin of a mammographic mass lesion to improve the classification of benign and malignant masses. Towards this goal, we designed features that measure the degree of sharpness and microlobulation of mass margins. We calculated these features in a border region of the mass defined as a thin band along the mass contour. The importance of these features in the classification of benign and malignant masses was studied in relation to existing features used for mammographic mass detection. Features were divided into three groups, each representing a different mass segment: the interior region of a mass, the border and the outer area. The interior and the outer area of a mass were characterized using contrast and spiculation measures. Classification was done in two steps. First, features representing each of the three mass segments were merged into a neural network classifier resulting in a single regional classification score for each segment. Secondly, a classifier combined the three single scores into a final output to discriminate between benign and malignant lesions. We compared the classification performance of each regional classifier and the combined classifier on a data set of 1076 biopsy proved masses (590 malignant and 486 benign) from 481 women included in the Digital Database for Screening Mammography. Receiver operating characteristic (ROC) analysis was used to evaluate the accuracy of the classifiers. The area under the ROC curve (Az) was 0.69 for the interior mass segment, 0.76 for the border segment and 0.75 for the outer mass segment. The performance of the combined classifier was 0.81 for image-based and 0.83 for case-based evaluation. These results show that the combination of information from different mass segments is an effective approach for computer-aided characterization of mammographic masses. An advantage of this approach is that it allows the assessment of the contribution of regions rather than individual features. Results suggest that the border and the outer areas contained the most valuable information for discrimination between benign and malignant masses.

Force Sensor Based Tool Condition Monitoring Using a Heterogeneous Ensemble Learning Model

PubMed Central

Wang, Guofeng; Yang, Yinwei; Li, Zhimeng

2014-01-01

Tool condition monitoring (TCM) plays an important role in improving machining efficiency and guaranteeing workpiece quality. In order to realize reliable recognition of the tool condition, a robust classifier needs to be constructed to depict the relationship between tool wear states and sensory information. However, because of the complexity of the machining process and the uncertainty of the tool wear evolution, it is hard for a single classifier to fit all the collected samples without sacrificing generalization ability. In this paper, heterogeneous ensemble learning is proposed to realize tool condition monitoring in which the support vector machine (SVM), hidden Markov model (HMM) and radius basis function (RBF) are selected as base classifiers and a stacking ensemble strategy is further used to reflect the relationship between the outputs of these base classifiers and tool wear states. Based on the heterogeneous ensemble learning classifier, an online monitoring system is constructed in which the harmonic features are extracted from force signals and a minimal redundancy and maximal relevance (mRMR) algorithm is utilized to select the most prominent features. To verify the effectiveness of the proposed method, a titanium alloy milling experiment was carried out and samples with different tool wear states were collected to build the proposed heterogeneous ensemble learning classifier. Moreover, the homogeneous ensemble learning model and majority voting strategy are also adopted to make a comparison. The analysis and comparison results show that the proposed heterogeneous ensemble learning classifier performs better in both classification accuracy and stability. PMID:25405514

Force sensor based tool condition monitoring using a heterogeneous ensemble learning model.

PubMed

Wang, Guofeng; Yang, Yinwei; Li, Zhimeng

2014-11-14

Tool condition monitoring (TCM) plays an important role in improving machining efficiency and guaranteeing workpiece quality. In order to realize reliable recognition of the tool condition, a robust classifier needs to be constructed to depict the relationship between tool wear states and sensory information. However, because of the complexity of the machining process and the uncertainty of the tool wear evolution, it is hard for a single classifier to fit all the collected samples without sacrificing generalization ability. In this paper, heterogeneous ensemble learning is proposed to realize tool condition monitoring in which the support vector machine (SVM), hidden Markov model (HMM) and radius basis function (RBF) are selected as base classifiers and a stacking ensemble strategy is further used to reflect the relationship between the outputs of these base classifiers and tool wear states. Based on the heterogeneous ensemble learning classifier, an online monitoring system is constructed in which the harmonic features are extracted from force signals and a minimal redundancy and maximal relevance (mRMR) algorithm is utilized to select the most prominent features. To verify the effectiveness of the proposed method, a titanium alloy milling experiment was carried out and samples with different tool wear states were collected to build the proposed heterogeneous ensemble learning classifier. Moreover, the homogeneous ensemble learning model and majority voting strategy are also adopted to make a comparison. The analysis and comparison results show that the proposed heterogeneous ensemble learning classifier performs better in both classification accuracy and stability.

Changes in quantitative 3D shape features of the optic nerve head associated with age

NASA Astrophysics Data System (ADS)

Christopher, Mark; Tang, Li; Fingert, John H.; Scheetz, Todd E.; Abramoff, Michael D.

2013-02-01

Optic nerve head (ONH) structure is an important biological feature of the eye used by clinicians to diagnose and monitor progression of diseases such as glaucoma. ONH structure is commonly examined using stereo fundus imaging or optical coherence tomography. Stereo fundus imaging provides stereo views of the ONH that retain 3D information useful for characterizing structure. In order to quantify 3D ONH structure, we applied a stereo correspondence algorithm to a set of stereo fundus images. Using these quantitative 3D ONH structure measurements, eigen structures were derived using principal component analysis from stereo images of 565 subjects from the Ocular Hypertension Treatment Study (OHTS). To evaluate the usefulness of the eigen structures, we explored associations with the demographic variables age, gender, and race. Using regression analysis, the eigen structures were found to have significant (p < 0.05) associations with both age and race after Bonferroni correction. In addition, classifiers were constructed to predict the demographic variables based solely on the eigen structures. These classifiers achieved an area under receiver operating characteristic curve of 0.62 in predicting a binary age variable, 0.52 in predicting gender, and 0.67 in predicting race. The use of objective, quantitative features or eigen structures can reveal hidden relationships between ONH structure and demographics. The use of these features could similarly allow specific aspects of ONH structure to be isolated and associated with the diagnosis of glaucoma, disease progression and outcomes, and genetic factors.

On Quantitative Biomarkers of VNS Therapy Using EEG and ECG Signals.

PubMed

Ravan, Maryam; Sabesan, Shivkumar; D'Cruz, O'Neill

2017-02-01

The goal of this work is to objectively evaluate the effectiveness of neuromodulation therapies, specifically, Vagus nerve stimulation (VNS) in reducing the severity of seizures in patients with medically refractory epilepsy. Using novel quantitative features obtained from combination of electroencephalographic (EEG) and electrocardiographic (ECG) signals around seizure events in 16 patients who underwent implantation of closed-loop VNS therapy system, namely AspireSR, we evaluated if automated delivery of VNS at the time of seizure onset reduces the severity of seizures by reducing EEG spatial synchronization as well as the duration and magnitude of heart rate increase. Unsupervised classification was subsequently applied to test the discriminative ability and validity of these features to measure responsiveness to VNS therapy. Results of application of this methodology to compare 105 pre-VNS treatment and 107 post-VNS treatment seizures revealed that seizures that were acutely stimulated using VNS had a reduced ictal spread as well as reduced impact on cardiovascular function compared to the ones that occurred prior to any treatment. Furthermore, application of an unsupervised fuzzy-c-mean classifier to evaluate the ability of the combined EEG-ECG based features to classify pre and post-treatment seizures achieved a classification accuracy of 85.85%. These results indicate the importance of timely delivery of VNS to reduce seizure severity and thus help achieve better seizure control for patients with epilepsy. The proposed set of quantitative features could be used as potential biomarkers for predicting long-term response to VNS therapy.

Unsupervised Pattern Classifier for Abnormality-Scaling of Vibration Features for Helicopter Gearbox Fault Diagnosis

NASA Technical Reports Server (NTRS)

Jammu, Vinay B.; Danai, Kourosh; Lewicki, David G.

1996-01-01

A new unsupervised pattern classifier is introduced for on-line detection of abnormality in features of vibration that are used for fault diagnosis of helicopter gearboxes. This classifier compares vibration features with their respective normal values and assigns them a value in (0, 1) to reflect their degree of abnormality. Therefore, the salient feature of this classifier is that it does not require feature values associated with faulty cases to identify abnormality. In order to cope with noise and changes in the operating conditions, an adaptation algorithm is incorporated that continually updates the normal values of the features. The proposed classifier is tested using experimental vibration features obtained from an OH-58A main rotor gearbox. The overall performance of this classifier is then evaluated by integrating the abnormality-scaled features for detection of faults. The fault detection results indicate that the performance of this classifier is comparable to the leading unsupervised neural networks: Kohonen's Feature Mapping and Adaptive Resonance Theory (AR72). This is significant considering that the independence of this classifier from fault-related features makes it uniquely suited to abnormality-scaling of vibration features for fault diagnosis.

A novel approach for food intake detection using electroglottography

PubMed Central

Farooq, Muhammad; Fontana, Juan M; Sazonov, Edward

2014-01-01

Many methods for monitoring diet and food intake rely on subjects self-reporting their daily intake. These methods are subjective, potentially inaccurate and need to be replaced by more accurate and objective methods. This paper presents a novel approach that uses an Electroglottograph (EGG) device for an objective and automatic detection of food intake. Thirty subjects participated in a 4-visit experiment involving the consumption of meals with self-selected content. Variations in the electrical impedance across the larynx caused by the passage of food during swallowing were captured by the EGG device. To compare performance of the proposed method with a well-established acoustical method, a throat microphone was used for monitoring swallowing sounds. Both signals were segmented into non-overlapping epochs of 30 s and processed to extract wavelet features. Subject-independent classifiers were trained using Artificial Neural Networks, to identify periods of food intake from the wavelet features. Results from leave-one-out cross-validation showed an average per-epoch classification accuracy of 90.1% for the EGG-based method and 83.1% for the acoustic-based method, demonstrating the feasibility of using an EGG for food intake detection. PMID:24671094

Soft computing-based terrain visual sensing and data fusion for unmanned ground robotic systems

NASA Astrophysics Data System (ADS)

Shirkhodaie, Amir

2006-05-01

In this paper, we have primarily discussed technical challenges and navigational skill requirements of mobile robots for traversability path planning in natural terrain environments similar to Mars surface terrains. We have described different methods for detection of salient terrain features based on imaging texture analysis techniques. We have also presented three competing techniques for terrain traversability assessment of mobile robots navigating in unstructured natural terrain environments. These three techniques include: a rule-based terrain classifier, a neural network-based terrain classifier, and a fuzzy-logic terrain classifier. Each proposed terrain classifier divides a region of natural terrain into finite sub-terrain regions and classifies terrain condition exclusively within each sub-terrain region based on terrain visual clues. The Kalman Filtering technique is applied for aggregative fusion of sub-terrain assessment results. The last two terrain classifiers are shown to have remarkable capability for terrain traversability assessment of natural terrains. We have conducted a comparative performance evaluation of all three terrain classifiers and presented the results in this paper.

Automatic classification of written descriptions by healthy adults: An overview of the application of natural language processing and machine learning techniques to clinical discourse analysis

PubMed Central

Toledo, Cíntia Matsuda; Cunha, Andre; Scarton, Carolina; Aluísio, Sandra

2014-01-01

Discourse production is an important aspect in the evaluation of brain-injured individuals. We believe that studies comparing the performance of brain-injured subjects with that of healthy controls must use groups with compatible education. A pioneering application of machine learning methods using Brazilian Portuguese for clinical purposes is described, highlighting education as an important variable in the Brazilian scenario. Objective The aims were to describe how to: (i) develop machine learning classifiers using features generated by natural language processing tools to distinguish descriptions produced by healthy individuals into classes based on their years of education; and (ii) automatically identify the features that best distinguish the groups. Methods The approach proposed here extracts linguistic features automatically from the written descriptions with the aid of two Natural Language Processing tools: Coh-Metrix-Port and AIC. It also includes nine task-specific features (three new ones, two extracted manually, besides description time; type of scene described – simple or complex; presentation order – which type of picture was described first; and age). In this study, the descriptions by 144 of the subjects studied in Toledo18 were used,which included 200 healthy Brazilians of both genders. Results and Conclusion A Support Vector Machine (SVM) with a radial basis function (RBF) kernel is the most recommended approach for the binary classification of our data, classifying three of the four initial classes. CfsSubsetEval (CFS) is a strong candidate to replace manual feature selection methods. PMID:29213908

Objective Data Assessment (ODA) Methods as Nutritional Assessment Tools.

PubMed

Hamada, Yasuhiro

2015-01-01

Nutritional screening and assessment should be a standard of care for all patients because nutritional management plays an important role in clinical practice. However, there is no gold standard for the diagnosis of malnutrition or undernutrition, although a large number of nutritional screening and assessment tools have been developed. Nutritional screening and assessment tools are classified into two categories, namely, subjective global assessment (SGA) and objective data assessment (ODA). SGA assesses nutritional status based on the features of medical history and physical examination. On the other hand, ODA consists of objective data provided from various analyses, such as anthropometry, bioimpedance analysis (BIA), dual-energy X-ray absorptiometry (DEXA), computed tomography (CT), magnetic resonance imaging (MRI), laboratory tests, and functional tests. This review highlights knowledge on the performance of ODA methods for the assessment of nutritional status in clinical practice. J. Med. Invest. 62: 119-122, August, 2015.

Less is more: Avoiding the LIBS dimensionality curse through judicious feature selection for explosive detection.

PubMed

Kumar Myakalwar, Ashwin; Spegazzini, Nicolas; Zhang, Chi; Kumar Anubham, Siva; Dasari, Ramachandra R; Barman, Ishan; Kumar Gundawar, Manoj

2015-08-19

Despite its intrinsic advantages, translation of laser induced breakdown spectroscopy for material identification has been often impeded by the lack of robustness of developed classification models, often due to the presence of spurious correlations. While a number of classifiers exhibiting high discriminatory power have been reported, efforts in establishing the subset of relevant spectral features that enable a fundamental interpretation of the segmentation capability and avoid the 'curse of dimensionality' have been lacking. Using LIBS data acquired from a set of secondary explosives, we investigate judicious feature selection approaches and architect two different chemometrics classifiers -based on feature selection through prerequisite knowledge of the sample composition and genetic algorithm, respectively. While the full spectral input results in classification rate of ca.92%, selection of only carbon to hydrogen spectral window results in near identical performance. Importantly, the genetic algorithm-derived classifier shows a statistically significant improvement to ca. 94% accuracy for prospective classification, even though the number of features used is an order of magnitude smaller. Our findings demonstrate the impact of rigorous feature selection in LIBS and also hint at the feasibility of using a discrete filter based detector thereby enabling a cheaper and compact system more amenable to field operations.

Less is more: Avoiding the LIBS dimensionality curse through judicious feature selection for explosive detection

PubMed Central

Kumar Myakalwar, Ashwin; Spegazzini, Nicolas; Zhang, Chi; Kumar Anubham, Siva; Dasari, Ramachandra R.; Barman, Ishan; Kumar Gundawar, Manoj

2015-01-01

Despite its intrinsic advantages, translation of laser induced breakdown spectroscopy for material identification has been often impeded by the lack of robustness of developed classification models, often due to the presence of spurious correlations. While a number of classifiers exhibiting high discriminatory power have been reported, efforts in establishing the subset of relevant spectral features that enable a fundamental interpretation of the segmentation capability and avoid the ‘curse of dimensionality’ have been lacking. Using LIBS data acquired from a set of secondary explosives, we investigate judicious feature selection approaches and architect two different chemometrics classifiers –based on feature selection through prerequisite knowledge of the sample composition and genetic algorithm, respectively. While the full spectral input results in classification rate of ca.92%, selection of only carbon to hydrogen spectral window results in near identical performance. Importantly, the genetic algorithm-derived classifier shows a statistically significant improvement to ca. 94% accuracy for prospective classification, even though the number of features used is an order of magnitude smaller. Our findings demonstrate the impact of rigorous feature selection in LIBS and also hint at the feasibility of using a discrete filter based detector thereby enabling a cheaper and compact system more amenable to field operations. PMID:26286630

Novel Features for Brain-Computer Interfaces

PubMed Central

Woon, W. L.; Cichocki, A.

2007-01-01

While conventional approaches of BCI feature extraction are based on the power spectrum, we have tried using nonlinear features for classifying BCI data. In this paper, we report our test results and findings, which indicate that the proposed method is a potentially useful addition to current feature extraction techniques. PMID:18364991

An intelligent support system for automatic detection of cerebral vascular accidents from brain CT images.

PubMed

Hajimani, Elmira; Ruano, M G; Ruano, A E

2017-07-01

This paper presents a Radial Basis Functions Neural Network (RBFNN) based detection system, for automatic identification of Cerebral Vascular Accidents (CVA) through analysis of Computed Tomographic (CT) images. For the design of a neural network classifier, a Multi Objective Genetic Algorithm (MOGA) framework is used to determine the architecture of the classifier, its corresponding parameters and input features by maximizing the classification precision, while ensuring generalization. This approach considers a large number of input features, comprising first and second order pixel intensity statistics, as well as symmetry/asymmetry information with respect to the ideal mid-sagittal line. Values of specificity of 98% and sensitivity of 98% were obtained, at pixel level, by an ensemble of non-dominated models generated by MOGA, in a set of 150 CT slices (1,867,602pixels), marked by a NeuroRadiologist. This approach also compares favorably at a lesion level with three other published solutions, in terms of specificity (86% compared with 84%), degree of coincidence of marked lesions (89% compared with 77%) and classification accuracy rate (96% compared with 88%). Copyright © 2017. Published by Elsevier B.V.

An approach for automatic classification of grouper vocalizations with passive acoustic monitoring.

PubMed

Ibrahim, Ali K; Chérubin, Laurent M; Zhuang, Hanqi; Schärer Umpierre, Michelle T; Dalgleish, Fraser; Erdol, Nurgun; Ouyang, B; Dalgleish, A

2018-02-01

Grouper, a family of marine fishes, produce distinct vocalizations associated with their reproductive behavior during spawning aggregation. These low frequencies sounds (50-350 Hz) consist of a series of pulses repeated at a variable rate. In this paper, an approach is presented for automatic classification of grouper vocalizations from ambient sounds recorded in situ with fixed hydrophones based on weighted features and sparse classifier. Group sounds were labeled initially by humans for training and testing various feature extraction and classification methods. In the feature extraction phase, four types of features were used to extract features of sounds produced by groupers. Once the sound features were extracted, three types of representative classifiers were applied to categorize the species that produced these sounds. Experimental results showed that the overall percentage of identification using the best combination of the selected feature extractor weighted mel frequency cepstral coefficients and sparse classifier achieved 82.7% accuracy. The proposed algorithm has been implemented in an autonomous platform (wave glider) for real-time detection and classification of group vocalizations.

Persistence of the Intuitive Conception of Living Things in Adolescence

NASA Astrophysics Data System (ADS)

Babai, Reuven; Sekal, Rachel; Stavy, Ruth

2010-02-01

This study investigated whether intuitive, naive conceptions of "living things" based on objects' mobility (movement = alive) persist into adolescence and affect 10th graders' accuracy of responses and reaction times during object classification. Most of the 58 students classified the test objects correctly as living/nonliving, yet they demonstrated significantly longer reaction times for classifying plants compared to animals and for classifying dynamic objects compared to static inanimate objects. Findings indicated that, despite prior learning in biology, the intuitive conception of living things persists up to age 15-16 years, affecting related reasoning processes. Consideration of these findings may help educators in their decisions about the nature of examples they use in their classrooms.

Symbolic feature detection for image understanding

NASA Astrophysics Data System (ADS)

Aslan, Sinem; Akgül, Ceyhun Burak; Sankur, Bülent

2014-03-01

In this study we propose a model-driven codebook generation method used to assign probability scores to pixels in order to represent underlying local shapes they reside in. In the first version of the symbol library we limited ourselves to photometric and similarity transformations applied on eight prototypical shapes of flat plateau , ramp, valley, ridge, circular and elliptic respectively pit and hill and used randomized decision forest as the statistical classifier to compute shape class ambiguity of each pixel. We achieved90% accuracy in identification of known objects from alternate views, however, we could not outperform texture, global and local shape methods, but only color-based method in recognition of unknown objects. We present a progress plan to be accomplished as a future work to improve the proposed approach further.

Classifying Structures in the ISM with Machine Learning Techniques

NASA Astrophysics Data System (ADS)

Beaumont, Christopher; Goodman, A. A.; Williams, J. P.

2011-01-01

The processes which govern molecular cloud evolution and star formation often sculpt structures in the ISM: filaments, pillars, shells, outflows, etc. Because of their morphological complexity, these objects are often identified manually. Manual classification has several disadvantages; the process is subjective, not easily reproducible, and does not scale well to handle increasingly large datasets. We have explored to what extent machine learning algorithms can be trained to autonomously identify specific morphological features in molecular cloud datasets. We show that the Support Vector Machine algorithm can successfully locate filaments and outflows blended with other emission structures. When the objects of interest are morphologically distinct from the surrounding emission, this autonomous classification achieves >90% accuracy. We have developed a set of IDL-based tools to apply this technique to other datasets.

Vehicle Detection in Aerial Images Based on Region Convolutional Neural Networks and Hard Negative Example Mining.

PubMed

Tang, Tianyu; Zhou, Shilin; Deng, Zhipeng; Zou, Huanxin; Lei, Lin

2017-02-10

Detecting vehicles in aerial imagery plays an important role in a wide range of applications. The current vehicle detection methods are mostly based on sliding-window search and handcrafted or shallow-learning-based features, having limited description capability and heavy computational costs. Recently, due to the powerful feature representations, region convolutional neural networks (CNN) based detection methods have achieved state-of-the-art performance in computer vision, especially Faster R-CNN. However, directly using it for vehicle detection in aerial images has many limitations: (1) region proposal network (RPN) in Faster R-CNN has poor performance for accurately locating small-sized vehicles, due to the relatively coarse feature maps; and (2) the classifier after RPN cannot distinguish vehicles and complex backgrounds well. In this study, an improved detection method based on Faster R-CNN is proposed in order to accomplish the two challenges mentioned above. Firstly, to improve the recall, we employ a hyper region proposal network (HRPN) to extract vehicle-like targets with a combination of hierarchical feature maps. Then, we replace the classifier after RPN by a cascade of boosted classifiers to verify the candidate regions, aiming at reducing false detection by negative example mining. We evaluate our method on the Munich vehicle dataset and the collected vehicle dataset, with improvements in accuracy and robustness compared to existing methods.

Predicting depression based on dynamic regional connectivity: a windowed Granger causality analysis of MEG recordings.

PubMed

Lu, Qing; Bi, Kun; Liu, Chu; Luo, Guoping; Tang, Hao; Yao, Zhijian

2013-10-16

Abnormal inter-regional causalities can be mapped for the objective diagnosis of various diseases. These inter-regional connectivities are usually calculated over an entire scan and used to characterize the stationary strength of the connections. However, the connectivity within networks may undergo substantial changes during a scan. In this study, we developed an objective depression recognition approach using the dynamic regional interactions that occur in response to sad facial stimuli. The whole time-period magnetoencephalography (MEG) signals from the visual cortex, amygdala, anterior cingulate cortex (ACC) and inferior frontal gyrus (IFG) were separated into sequential time intervals. The Granger causality mapping method was used to identify the pairwise interaction pattern within each time interval. Feature selection was then undertaken within a minimum redundancy-maximum relevance (mRMR) framework. Typical classifiers were utilized to predict those patients who had depression. The overall performances of these classifiers were similar, and the highest classification accuracy rate was 87.5%. The best discriminative performance was obtained when the number of features was within a robust range. The discriminative network pattern obtained through support vector machine (SVM) analyses displayed abnormal causal connectivities that involved the amygdala during the early and late stages. These early and late connections in the amygdala appear to reveal a negative bias to coarse expression information processing and abnormal negative modulation in patients with depression, which may critically affect depression discrimination. © 2013 Elsevier B.V. All rights reserved.

OpenCL based machine learning labeling of biomedical datasets

NASA Astrophysics Data System (ADS)

Amoros, Oscar; Escalera, Sergio; Puig, Anna

2011-03-01

In this paper, we propose a two-stage labeling method of large biomedical datasets through a parallel approach in a single GPU. Diagnostic methods, structures volume measurements, and visualization systems are of major importance for surgery planning, intra-operative imaging and image-guided surgery. In all cases, to provide an automatic and interactive method to label or to tag different structures contained into input data becomes imperative. Several approaches to label or segment biomedical datasets has been proposed to discriminate different anatomical structures in an output tagged dataset. Among existing methods, supervised learning methods for segmentation have been devised to easily analyze biomedical datasets by a non-expert user. However, they still have some problems concerning practical application, such as slow learning and testing speeds. In addition, recent technological developments have led to widespread availability of multi-core CPUs and GPUs, as well as new software languages, such as NVIDIA's CUDA and OpenCL, allowing to apply parallel programming paradigms in conventional personal computers. Adaboost classifier is one of the most widely applied methods for labeling in the Machine Learning community. In a first stage, Adaboost trains a binary classifier from a set of pre-labeled samples described by a set of features. This binary classifier is defined as a weighted combination of weak classifiers. Each weak classifier is a simple decision function estimated on a single feature value. Then, at the testing stage, each weak classifier is independently applied on the features of a set of unlabeled samples. In this work, we propose an alternative representation of the Adaboost binary classifier. We use this proposed representation to define a new GPU-based parallelized Adaboost testing stage using OpenCL. We provide numerical experiments based on large available data sets and we compare our results to CPU-based strategies in terms of time and labeling speeds.

Real-time vibration-based structural damage detection using one-dimensional convolutional neural networks

NASA Astrophysics Data System (ADS)

Abdeljaber, Osama; Avci, Onur; Kiranyaz, Serkan; Gabbouj, Moncef; Inman, Daniel J.

2017-02-01

Structural health monitoring (SHM) and vibration-based structural damage detection have been a continuous interest for civil, mechanical and aerospace engineers over the decades. Early and meticulous damage detection has always been one of the principal objectives of SHM applications. The performance of a classical damage detection system predominantly depends on the choice of the features and the classifier. While the fixed and hand-crafted features may either be a sub-optimal choice for a particular structure or fail to achieve the same level of performance on another structure, they usually require a large computation power which may hinder their usage for real-time structural damage detection. This paper presents a novel, fast and accurate structural damage detection system using 1D Convolutional Neural Networks (CNNs) that has an inherent adaptive design to fuse both feature extraction and classification blocks into a single and compact learning body. The proposed method performs vibration-based damage detection and localization of the damage in real-time. The advantage of this approach is its ability to extract optimal damage-sensitive features automatically from the raw acceleration signals. Large-scale experiments conducted on a grandstand simulator revealed an outstanding performance and verified the computational efficiency of the proposed real-time damage detection method.